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

    Neuronpedia

    INDEX
    Explanations

    use cases and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     useful
    1.46
    用於
    1.31
     Useful
    1.20
    运算
    1.09
    なります
    1.06
    जिस
    1.04
    用戶
    1.04
     ఉపయోగ
    1.03
    טים
    1.03
     कहने
    1.00
    POSITIVE LOGITS
    fulness
    1.73
    FUL
    1.69
    fully
    1.39
     sparingly
    1.39
    CreateIndex
    1.36
    िता
    1.32
     discretion
    1.20
    age
    1.19
    NewUrlParser
    1.17
    戶
    1.17
    Act Density 0.417%

    No Known Activations