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

    Neuronpedia

    INDEX
    Explanations

    list items or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     despre
    0.45
     vessel
    0.44
     ving
    0.44
    星座
    0.43
    빙
    0.43
     duc
    0.43
     mappe
    0.41
     sidd
    0.40
     Kanton
    0.39
     imediat
    0.39
    POSITIVE LOGITS
    >";
    0.48
     ဆို
    0.48
    ponsor
    0.45
     الألم
    0.44
    ódromo
    0.44
     必要
    0.44
    流畅
    0.43
    >");
    0.41
     A
    0.41
    ែម
    0.41
    Act Density 0.000%

    No Known Activations