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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    completion
    0.82
    жением
    0.81
    czny
    0.80
    ченных
    0.75
     загряз
    0.74
    frac
    0.73
    нным
    0.73
    between
    0.72
    нных
    0.72
    ة
    0.72
    POSITIVE LOGITS
     thủ
    0.74
     tassa
    0.70
     inc
    0.68
     taxes
    0.67
     版本
    0.66
     Burmese
    0.66
     наві
    0.66
     історії
    0.66
     noto
    0.65
     puissiez
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.