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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ’
    0.58
    CC
    0.54
    א
    0.50
    (
    0.49
    epi
    0.49
    CA
    0.48
    HM
    0.48
    *
    0.48
    about
    0.48
    .’
    0.48
    POSITIVE LOGITS
    ঙ্গিক
    0.57
    在
    0.55
     Bloc
    0.54
     Handlung
    0.54
     größ
    0.54
    衡
    0.53
    વવા
    0.52
     Lehrer
    0.51
     legjobb
    0.51
     Langer
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.