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

    Neuronpedia

    INDEX
    Explanations

    device or new web

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pw
    0.75
    itted
    0.72
    чения
    0.71
    p
    0.71
    sw
    0.71
    pi
    0.70
    md
    0.68
    tage
    0.67
    sm
    0.67
    arantine
    0.67
    POSITIVE LOGITS
     lengan
    0.98
    Բ
    0.98
    ۰
    0.90
    ັດ
    0.90
     bersifat
    0.88
     twórc
    0.86
     Δια
    0.86
    ໌
    0.82
    Sumber
    0.82
     voud
    0.80
    Act Density 0.012%

    No Known Activations