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

    Neuronpedia

    INDEX
    Explanations

    just a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hereinafter
    0.46
     चलती
    0.43
     удовлетво
    0.41
    powied
    0.40
    putBoolean
    0.40
    aughlin
    0.40
    㞖
    0.39
     প্রজাত
    0.39
    Pherson
    0.39
    viel
    0.38
    POSITIVE LOGITS
    成長
    0.41
     ~
    0.41
    ﺧ
    0.40
    Un
    0.40
    مل
    0.40
    ت
    0.40
    زه
    0.40
    يز
    0.39
     *
    0.39
    ز
    0.38
    Act Density 0.001%

    No Known Activations