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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conditional processing or error handling in code

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

    Code-related tokens, e.g., operators or file extensions

    np_acts-logits-general · gemini-2.0-flash

    const, function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $^{\
    -0.58
     jScrollPane
    -0.57
     []*
    -0.57
     PLWABN
    -0.55
    Portail
    -0.54
     betweenstory
    -0.53
     jspb
    -0.52
     kaynağından
    -0.52
    TemporalType
    -0.52
     himo
    -0.52
    POSITIVE LOGITS
    const
    0.61
     const
    0.60
    }),
    0.60
    StoreMessageInfo
    0.57
    ']),
    0.55
    '],
    0.55
    keyframes
    0.52
     AUTHORITY
    0.51
    ']],
    0.49
    IsContent
    0.49
    Act Density 0.027%

    No Known Activations