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

    Neuronpedia

    INDEX
    Explanations

    key policy best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otto
    0.47
    asko
    0.47
    phas
    0.46
     divorce
    0.45
    parametri
    0.45
    .”
    0.45
    ,”
    0.45
    meni
    0.44
    ietta
    0.44
     ”,
    0.44
    POSITIVE LOGITS
    壳
    0.45
    ية
    0.42
    )\,
    0.42
     ステン
    0.40
    ում
    0.40
     técnicas
    0.40
    ்ய
    0.39
    厚
    0.39
    ের
    0.39
    绸
    0.39
    Act Density 0.000%

    No Known Activations