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

    Neuronpedia

    INDEX
    Explanations

    snack bar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infiltration
    0.43
     dernier
    0.42
     안전
    0.41
     നടത്തിയ
    0.40
     vettore
    0.39
     komponent
    0.39
     শতাংশ
    0.39
     fournir
    0.39
    тні
    0.39
     canale
    0.38
    POSITIVE LOGITS
    conversion
    0.37
    DB
    0.35
    Operation
    0.34
    协议
    0.34
     ♪
    0.34
    AV
    0.33
    Upload
    0.33
    DW
    0.33
    BEGIN
    0.33
    mang
    0.33
    Act Density 0.003%

    No Known Activations