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

    Neuronpedia

    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    én
    -0.07
     healer
    -0.06
    -master
    -0.06
    ζί
    -0.06
    _RAM
    -0.06
     sexkontakte
    -0.06
    eping
    -0.06
     setter
    -0.06
    ogany
    -0.06
    dí
    -0.06
    POSITIVE LOGITS
    .ba
    0.06
     पढ
    0.06
     Distribution
    0.06
     automat
    0.06
     후보
    0.06
     продуктов
    0.06
    _SHIFT
    0.06
    は
    0.06
     나오
    0.06
    급
    0.06
    Act Density 0.009%

    No Known Activations