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

    Neuronpedia

    INDEX
    Explanations

    route path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ها
    0.66
     Westchester
    0.66
    l
    0.62
    मधील
    0.60
    ра
    0.59
    。
    0.59
     termino
    0.58
    uruan
    0.57
    न्
    0.56
     a
    0.56
    POSITIVE LOGITS
    นั่ง
    0.71
    न
    0.70
    ن
    0.67
     for
    0.66
    ন
    0.63
    νες
    0.62
    ⚭
    0.61
    尣
    0.60
    spě
    0.59
    েল
    0.58
    Act Density 0.000%

    No Known Activations