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

    Neuronpedia

    INDEX
    Explanations

    sequences of 0 and 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    2.80
    ص
    2.20
    ح
    1.97
    ce
    1.63
    د
    1.61
    le
    1.55
     escre
    1.55
    েল
    1.50
    ز
    1.49
    с
    1.48
    POSITIVE LOGITS
    ía
    1.55
    MNOP
    1.55
    们
    1.54
    EO
    1.48
    ००
    1.48
    amani
    1.48
    ATE
    1.47
    Não
    1.47
    目的是
    1.47
    ND
    1.45
    Act Density 0.073%

    No Known Activations