Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or data structures.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    things related to programming code snippets.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    repeated patterns or sequences in structured data or code.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Alphanumeric and hexadecimal codes or identifiers

    np_acts-logits-general · gemini-2.0-flash

    code structures with hexadecimal values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HttpFoundation
    -0.48
    entuh
    -0.46
     Brande
    -0.45
     sens
    -0.45
    rie
    -0.43
    googleapis
    -0.42
     deb
    -0.42
    довлет
    -0.41
    MockMvc
    -0.41
     effective
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.79
    mybatisplus
    0.79
     SwitchCompat
    0.76
     Roskov
    0.73
     يتيمه
    0.70
     للاسماء
    0.70
     ];
    0.69
    ];
    0.67
     متعلقه
    0.65
    '][]
    0.65
    Act Density 0.163%

    No Known Activations