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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proizvoda
    1.00
     तरीके
    0.96
    don
    0.96
    0
    0.96
    ٠
    0.96
     Узбеки
    0.91
     zejména
    0.90
    Ę
    0.86
     コンパクト
    0.86
     bárm
    0.86
    POSITIVE LOGITS
     the
    1.19
     a
    1.05
    );
    1.04
    ;
    1.01
    ),
    0.93
    )
    0.90
     their
    0.89
    the
    0.84
    )،
    0.80
    ;;)
    0.80
    Act Density 0.703%

    No Known Activations