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

    Neuronpedia

    INDEX
    Explanations

    software, duel, color, transfer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    도
    0.83
    ين
    0.81
    نا
    0.80
    ج
    0.80
    و
    0.74
    -
    0.72
    ف
    0.71
    ३
    0.70
    in
    0.69
    ও
    0.68
    POSITIVE LOGITS
     is
    1.05
    0.89
     the
    0.75
     my
    0.66
    )
    0.64
     at
    0.63
    }
    0.63
     roaring
    0.61
     ก
    0.58
     Europäischen
    0.58
    Act Density 0.378%

    No Known Activations