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

    Neuronpedia

    INDEX
    Explanations

    braces and structural elements commonly used in programming syntax

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    code block closing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unwin
    -0.74
    andExpect
    -0.71
    ButterKnife
    -0.71
    mbh
    -0.69
    olerance
    -0.68
     Mahi
    -0.68
    unknownFields
    -0.68
    mani
    -0.67
    Sami
    -0.67
    FieldDescriptor
    -0.67
    POSITIVE LOGITS
    "},
    0.75
    )))
    0.74
    ":[{
    0.73
     ]
    0.72
    "])
    0.72
    InitStruct
    0.69
    ThroughAttribute
    0.69
    ".
    0.68
    ska
    0.67
    )
    0.66
    Act Density 0.059%

    No Known Activations