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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    factorplot
    0.81
    pronged
    0.80
     попы
    0.78
     tentativas
    0.77
     escol
    0.76
     Richtung
    0.75
     obligation
    0.75
    toolStripButton
    0.75
     dawned
    0.74
     deleteTask
    0.74
    POSITIVE LOGITS
    ش
    0.84
    िट
    0.80
    েল
    0.75
    س
    0.74
    ку
    0.73
    ਟ
    0.73
    شى
    0.72
    კის
    0.71
    作曲
    0.71
    ت
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.