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

    Neuronpedia

    INDEX
    Explanations

    movie titles and books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.97
     excl
    0.87
    ó
    0.86
     enferm
    0.85
     restent
    0.84
    }"/>
    0.84
    s
    0.84
    ל
    0.84
    वहीं
    0.82
    ના
    0.82
    POSITIVE LOGITS
    ী
    1.23
     비롯
    1.14
    من
    1.10
    でに
    1.09
    یشه
    1.07
    ین
    1.06
    ように
    1.05
    inicio
    1.04
    ist
    1.02
    ์
    1.02
    Act Density 0.025%

    No Known Activations