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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ignty
    -0.74
    ailand
    -0.72
    opsis
    -0.70
    ramids
    -0.67
     DVDs
    -0.66
    rehend
    -0.65
    creator
    -0.65
    reason
    -0.64
    modules
    -0.64
    cffff
    -0.64
    POSITIVE LOGITS
    ij士
    0.77
    Īè
    0.75
     Admir
    0.72
     largeDownload
    0.69
    Ĭ±
    0.67
    ADRA
    0.65
     Schwar
    0.65
     suicide
    0.65
     Alz
    0.64
     Bomber
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.