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

    Neuronpedia

    INDEX
    Explanations

    stainless steel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    어
    0.67
    ;
    0.65
    ﹊
    0.59
    圤
    0.57
     Apostle
    0.56
     THROUGH
    0.55
    لي
    0.54
    А
    0.53
    ای
    0.53
    Aeonium
    0.53
    POSITIVE LOGITS
    ו
    0.94
     can
    0.92
    ี
    0.89
    ร
    0.89
    ar
    0.86
    ا
    0.86
    و
    0.80
    et
    0.80
     be
    0.80
    ר
    0.79
    Act Density 0.000%

    No Known Activations