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

    Neuronpedia

    INDEX
    Explanations

    key elements related to questioning or exploring knowledge

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

    charge or treatment following certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsxFileName
    -0.58
    帖最后由
    -0.45
    ConstraintMaker
    -0.43
     noDo
    -0.43
    flink
    -0.39
     AssemblyCompany
    -0.36
    Sklici
    -0.35
    justed
    -0.34
     myſelf
    -0.34
     implied
    -0.34
    POSITIVE LOGITS
     ModelExpression
    0.51
    Vidite
    0.46
     ProtoMessage
    0.43
    sidemargin
    0.42
    exitRule
    0.42
    лтемелер
    0.41
    findpost
    0.41
    WireFormatLite
    0.41
    WriteAttribute
    0.40
    aarrggbb
    0.38
    Act Density 0.055%

    No Known Activations