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

    Neuronpedia

    INDEX
    Explanations

    quell that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    0.69
     (
    0.65
    '
    0.65
     A
    0.64
    re
    0.61
    '.
    0.57
     În
    0.57
    "),
    0.56
    sp
    0.55
    ia
    0.55
    POSITIVE LOGITS
    ও
    1.00
     σε
    0.84
    も
    0.84
    ز
    0.77
    ین
    0.72
    もら
    0.70
    ق
    0.69
    ຂອງ
    0.68
    𝟑
    0.67
    도
    0.67
    Act Density 4.515%

    No Known Activations