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

    Neuronpedia

    INDEX
    Explanations

    new daily counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     now
    -0.93
     τὸν
    -0.84
    unna
    -0.84
     đời
    -0.81
     теперь
    -0.81
    quants
    -0.80
     nib
    -0.77
     kiệm
    -0.77
     ultimately
    -0.73
     adecuado
    -0.73
    POSITIVE LOGITS
     daily
    1.39
     yesterday
    1.35
     yeni
    1.25
     day
    1.18
     new
    1.17
     очеред
    1.13
     overnight
    1.13
     új
    1.11
    新的
    1.10
    新增
    1.09
    Act Density 0.009%

    No Known Activations