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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    variant
    0.53
    Stevens
    0.51
    t
    0.51
    Src
    0.50
    Lai
    0.49
     সংস্করণ
    0.48
    Nik
    0.48
     Auflage
    0.48
    edge
    0.47
     Grundlage
    0.46
    POSITIVE LOGITS
     favours
    0.49
     odour
    0.48
     SAME
    0.47
    がお
    0.47
    ने
    0.46
    總
    0.46
     specialises
    0.46
     theatres
    0.46
     THEIR
    0.46
     WHEN
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.