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

    Neuronpedia

    INDEX
    Explanations

    Jean followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    2.06
    h
    1.87
    j
    1.85
    haz
    1.77
    tau
    1.76
    ti
    1.73
    ties
    1.70
    ean
    1.69
    ted
    1.66
    jb
    1.64
    POSITIVE LOGITS
    ला
    1.96
    ATION
    1.83
    攵
    1.80
    {
    1.76
    ين
    1.72
    嘛
    1.61
     santé
    1.54
     осно
    1.54
    ین
    1.52
    $
    1.52
    Act Density 0.002%

    No Known Activations