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

    Neuronpedia

    INDEX
    Explanations

    buy or sell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gemeins
    0.85
    wegs
    0.79
     ^
    0.74
    elig
    0.73
     wissen
    0.72
    ean
    0.71
     egent
    0.70
     eks
    0.70
     bruger
    0.69
     tragen
    0.69
    POSITIVE LOGITS
    多家
    0.83
    剧情
    0.81
     시리즈
    0.79
     GPL
    0.79
    댓글
    0.79
    严重的
    0.79
    ي
    0.78
    민국
    0.77
    摩托
    0.77
    他的
    0.76
    Act Density 0.003%

    No Known Activations