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

    Neuronpedia

    INDEX
    Explanations

    eventually brought, offers can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၀၀
    0.48
    ethash
    0.45
     no
    0.45
     необходимо
    0.44
    ность
    0.43
    ক্ষা
    0.43
     ছাত্র
    0.42
     温度
    0.42
    ARD
    0.42
     শো
    0.42
    POSITIVE LOGITS
    i
    0.43
    软
    0.43
    贫
    0.42
    न
    0.41
    Purch
    0.41
    reden
    0.40
    疯狂
    0.40
    ?
    0.40
    선
    0.39
    ن
    0.39
    Act Density 0.002%

    No Known Activations