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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     endorsement
    -0.07
     Characteristics
    -0.07
    什么样的
    -0.07
    𫌀
    -0.07
     tipo
    -0.07
     ~=
    -0.07
    ﯧ
    -0.07
    .Abstractions
    -0.07
    튭
    -0.06
    _Selection
    -0.06
    POSITIVE LOGITS
    here
    0.08
    WO
    0.07
    _FREQ
    0.07
    rolling
    0.07
    лон
    0.06
    leş
    0.06
    ブランド
    0.06
    olan
    0.06
    (place
    0.06
     mushroom
    0.06
    Act Density 0.001%

    No Known Activations