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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tiered
    0.75
     पंचायत
    0.72
    baran
    0.70
    classifier
    0.69
    objc
    0.69
     Device
    0.68
    シーン
    0.68
    賈
    0.68
    椛
    0.68
    データ
    0.67
    POSITIVE LOGITS
    in
    1.03
    h
    0.93
    me
    0.85
    hão
    0.84
     wann
    0.80
     hiç
    0.80
     basta
    0.79
     gills
    0.77
     กลับ
    0.77
    inness
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.