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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     finitely
    1.08
     publishers
    0.97
     oxidized
    0.97
     acrylic
    0.94
    建立了
    0.93
     academies
    0.92
     mica
    0.92
     harshly
    0.91
     defiant
    0.91
     oxidizing
    0.91
    POSITIVE LOGITS
    s
    0.92
    ící
    0.88
    zés
    0.88
    ítés
    0.85
    onavírus
    0.84
    ми
    0.84
    viä
    0.82
    ве
    0.82
    ным
    0.82
    вся
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.