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

    Neuronpedia

    INDEX
    Explanations

    python import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.03
    ।)
    0.93
     únicamente
    0.92
     comentários
    0.92
    )。
    0.92
    )।
    0.90
     alcun
    0.88
     parecía
    0.88
     decía
    0.85
    ។
    0.84
    POSITIVE LOGITS
     of
    0.86
    at
    0.80
     British
    0.69
     (
    0.68
    op
    0.64
     System
    0.64
    ofthe
    0.63
     with
    0.63
     Sesame
    0.63
    over
    0.61
    Act Density 0.000%

    No Known Activations