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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _org
    -0.07
     leak
    -0.07
     reveals
    -0.07
    _count
    -0.07
     indispensable
    -0.07
     induce
    -0.07
    sol
    -0.07
    [index
    -0.06
     skeptic
    -0.06
    皕
    -0.06
    POSITIVE LOGITS
    ustomed
    0.08
    achs
    0.07
     Cinema
    0.07
    BM
    0.07
    umberland
    0.07
     ALLOW
    0.07
    �
    0.07
    全力以
    0.07
    äche
    0.07
    ꙳
    0.07
    Act Density 0.009%

    No Known Activations