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

    Neuronpedia

    INDEX
    Explanations

    це / это + explanatory noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    에
    1.73
     DRM
    1.57
    ام
    1.52
    이면
    1.48
    必要があります
    1.48
    ت
    1.48
     tux
    1.45
     kinks
    1.43
     GBM
    1.41
    ش
    1.41
    POSITIVE LOGITS
    gruppe
    2.06
    rische
    1.93
    <0x80>
    1.90
    gestellt
    1.89
    tai
    1.88
    garten
    1.88
    ecek
    1.80
    kennung
    1.79
    1.78
    gro
    1.76
    Act Density 0.009%

    No Known Activations