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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Assange
    1.03
    <unused235>
    1.02
     Hermitian
    1.02
     Globally
    1.01
     stickers
    1.01
    <unused1116>
    1.00
    гал
    1.00
     ngram
    0.98
    <unused1823>
    0.98
     Nort
    0.97
    POSITIVE LOGITS
     stare
    0.95
     い
    0.92
     journée
    0.87
     حدث
    0.85
     kung
    0.84
     meal
    0.83
     בי
    0.82
    loch
    0.81
    adihi
    0.80
     settlement
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.