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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming or defined structures in code

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

    Strings/code in languages other than English

    np_acts-logits-general · gemini-2.0-flash

    XML tags and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ters
    -0.53
    ondi
    -0.52
    TERN
    -0.49
     lo
    -0.49
    chev
    -0.48
    죠
    -0.48
    enko
    -0.47
    ringes
    -0.47
     amp
    -0.46
     sa
    -0.46
    POSITIVE LOGITS
     '\\;'
    1.08
     كومونز
    1.00
     мәкал
    0.98
     Baillargeon
    0.97
     متعلقه
    0.95
     незавершена
    0.93
    ########.
    0.91
    +#+
    0.89
     Roskov
    0.88
    ]")]
    0.87
    Act Density 0.186%

    No Known Activations