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

    Neuronpedia

    INDEX
    Explanations

    state-of-the-art facilities and equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.93
    на
    0.86
    ي
    0.82
    ل
    0.81
    י
    0.79
    ang
    0.79
    il
    0.78
    ่
    0.77
    in
    0.76
    ร
    0.76
    POSITIVE LOGITS
     of
    0.73
    cua
    0.59
    ኋ
    0.59
    ',
    0.57
     erected
    0.56
     ofx
    0.55
    trs
    0.54
    ಂಡ
    0.54
    *',
    0.54
     penguins
    0.53
    Act Density 0.000%

    No Known Activations