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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Const
    -0.72
    ãĤ±
    -0.66
     inconsistencies
    -0.63
    Action
    -0.63
     soap
    -0.62
    esp
    -0.61
     hasht
    -0.60
    ãģ®å
    -0.60
    ļéĨĴ
    -0.60
    Accessory
    -0.59
    POSITIVE LOGITS
    lehem
    0.81
    cean
    0.77
    MIN
    0.70
    rament
    0.68
    chnology
    0.68
    enza
    0.67
    heit
    0.64
    ENDED
    0.63
     Gleaming
    0.62
    ndra
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.