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

    Neuronpedia

    INDEX
    Explanations

    immortality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cento
    1.87
    لیکن
    1.79
    л
    1.77
    u
    1.75
     volta
    1.71
    denly
    1.62
     awhile
    1.54
    ET
    1.54
    gies
    1.49
    correcto
    1.45
    POSITIVE LOGITS
    くちゃ
    1.60
     peserta
    1.39
    เคล
    1.36
    pekte
    1.30
    뺀
    1.30
     miejsca
    1.29
     곳
    1.29
    ని
    1.29
    veloppement
    1.28
    ‌اند
    1.28
    Act Density 0.000%

    No Known Activations