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

    Neuronpedia

    INDEX
    Explanations

    say "mod"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adat
    -0.08
    ，实现
    -0.07
     analog
    -0.07
    ot
    -0.07
    det
    -0.07
    Trad
    -0.07
     trilogy
    -0.07
    .replace
    -0.07
    .set
    -0.07
     éton
    -0.07
    POSITIVE LOGITS
     Keine
    0.11
     Weitere
    0.10
     અત્યાર
    0.10
     противопоказ
    0.09
    查看更多
    0.09
     ఇత
    0.09
     Пока
    0.09
     الأخير
    0.09
     搜
    0.09
     kleinere
    0.09
    Act Density 0.003%

    No Known Activations