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

    Neuronpedia

    INDEX
    Explanations

    programmatic asynchronous operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    1.03
    al
    0.96
    ur
    0.95
    0.93
    㛣
    0.87
    oo
    0.83
     If
    0.82
     А
    0.82
    oon
    0.81
    urized
    0.80
    POSITIVE LOGITS
    ف
    1.12
    to
    0.96
    ك
    0.91
    その
    0.88
    сного
    0.84
    შ
    0.81
    де
    0.81
    يد
    0.80
    ی
    0.80
    خود
    0.79
    Act Density 0.030%

    No Known Activations