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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    و
    1.16
    ি
    1.09
     все
    1.04
    ol
    0.98
     основ
    0.97
     ३
    0.95
     роди
    0.95
     neun
    0.95
     кло
    0.94
    ोत
    0.93
    POSITIVE LOGITS
    S
    1.89
    ع
    1.59
    C
    1.56
    R
    1.52
     or
    1.48
    F
    1.45
    V
    1.44
    L
    1.42
    H
    1.40
    ح
    1.30
    Act Density 0.000%

    No Known Activations