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

    Neuronpedia

    INDEX
    Explanations

    f-string formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.13
    am
    1.03
    வும்
    1.01
     thoughts
    0.99
     thumbs
    0.97
    ние
    0.97
    at
    0.93
    ين
    0.90
     publishers
    0.89
     small
    0.87
    POSITIVE LOGITS
    ografica
    1.09
     jornadas
    0.99
     possui
    0.99
    屣
    0.98
     hérit
    0.98
     рамках
    0.94
     Jorn
    0.94
    ヴェ
    0.93
    attform
    0.93
     llegada
    0.92
    Act Density 0.029%

    No Known Activations