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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vironments
    -0.72
    umbledore
    -0.72
    */(
    -0.69
     Izan
    -0.69
     CLSID
    -0.66
    ortunately
    -0.64
    otyp
    -0.64
    urations
    -0.63
    ocamp
    -0.62
    ovember
    -0.62
    POSITIVE LOGITS
    Sources
    0.72
    ICK
    0.69
    MAC
    0.68
     Secrets
    0.65
    MAG
    0.65
    Charges
    0.63
    AC
    0.63
    Shares
    0.63
    cci
    0.63
    IRD
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.