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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     because
    -1.61
    _
    -1.60
     if
    -1.57
    u
    -1.57
    ！"
    -1.51
    carnated
    -1.45
     allows
    -1.39
     zaradi
    -1.38
    when
    -1.36
     теря
    -1.36
    POSITIVE LOGITS
    niño
    1.65
     cuadro
    1.61
    瞜
    1.60
    鷽
    1.52
    ？】
    1.52
     違い
    1.52
    stopwatch
    1.52
     ninguno
    1.49
     conqu
    1.48
     tremend
    1.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.