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

    Neuronpedia

    INDEX
    Explanations

    integer division or comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    1.70
    i
    1.57
    z
    1.55
    ي
    1.42
    다
    1.30
    y
    1.23
    m
    1.19
    t
    1.13
    l
    1.09
    ר
    1.09
    POSITIVE LOGITS
    خ
    1.20
    Описание
    0.96
     afectados
    0.82
    ün
    0.81
    idade
    0.80
     integrantes
    0.80
    خراج
    0.80
    timevals
    0.80
    izados
    0.79
    માં
    0.78
    Act Density 0.009%

    No Known Activations