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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ombil
    0.97
     molti
    0.96
     과정을
    0.96
    icidal
    0.93
    ohan
    0.93
     Moderators
    0.91
    aks
    0.91
     익
    0.89
    կ
    0.89
    ения
    0.88
    POSITIVE LOGITS
    LDA
    0.83
    بر
    0.81
    Relative
    0.81
    finding
    0.80
    ف
    0.80
    رو
    0.79
    Tried
    0.79
    pointing
    0.79
    驢
    0.78
     logically
    0.77
    Act Density 0.000%

    No Known Activations