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

    Neuronpedia

    INDEX
    Explanations

    non-word characters or whitespace sequences

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

    Non-English programming or markup

    np_acts-logits-general · gemini-2.0-flash

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.61
     بلغ
    -0.58
    گاب
    -0.57
    RequestParam
    -0.55
     isEqualToString
    -0.54
    rifft
    -0.54
     Marg
    -0.53
     """",
    -0.51
    Late
    -0.50
     Pink
    -0.50
    POSITIVE LOGITS
    \{\\
    0.84
    存于互联网档案馆
    0.82
    tagHelperRunner
    0.72
    protoimpl
    0.72
     الحره
    0.68
     وتسجيلات
    0.67
    ])]
    0.65
     الرياضيه
    0.63
    tableFuture
    0.63
    UnknownFieldSet
    0.62
    Act Density 0.135%

    No Known Activations