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

    Neuronpedia

    INDEX
    Explanations

    general knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     really
    0.75
    ходи
    0.67
    нова
    0.67
    anj
    0.65
     conditions
    0.63
     غير
    0.63
     Really
    0.62
    zza
    0.62
     do
    0.62
     nanti
    0.62
    POSITIVE LOGITS
     Cloth
    1.06
    <unused464>
    1.05
    visible
    1.05
     영어
    1.05
     англий
    1.04
     Riley
    1.03
     draped
    1.02
     영국
    1.02
     बॉलीवुड
    1.01
     관심
    1.01
    Act Density 0.000%

    No Known Activations