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

    Neuronpedia

    INDEX
    Explanations

    string formatting operations in code

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

    constructor detail, method summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.62
     initComponents
    -0.56
     InputDecoration
    -0.56
     Италијани
    -0.53
    TypedDataSet
    -0.53
    InputBorder
    -0.51
     betweenstory
    -0.50
     ProtoMessage
    -0.49
     soeur
    -0.48
    SharedDtor
    -0.47
    POSITIVE LOGITS
    matchCondition
    1.86
    DebuggerNonUser
    0.48
     transfieras
    0.41
    TokenNameLPAREN
    0.40
     dirigez
    0.39
    Kind
    0.38
    মান
    0.37
    おめでとうございます
    0.37
     autorytatywna
    0.36
    ValueStyle
    0.35
    Act Density 0.005%

    No Known Activations