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

    Neuronpedia

    INDEX
    Explanations

    10⁴

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    произ
    0.41
    시면
    0.40
     subcommand
    0.40
     truths
    0.39
     eût
    0.39
    蹼
    0.38
    ثمان
    0.38
    знача
    0.37
     outermost
    0.37
    ขาว
    0.37
    POSITIVE LOGITS
    克力
    0.40
     Nep
    0.39
     Nase
    0.39
    ae
    0.38
    immer
    0.38
     Major
    0.38
    elser
    0.38
     Mi
    0.38
    emi
    0.38
    Mi
    0.38
    Act Density 0.000%

    No Known Activations