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

    Neuronpedia

    INDEX
    Explanations

    easier scaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fub
    0.85
     portato
    0.78
    モリ
    0.77
     território
    0.75
     disipl
    0.74
     current
    0.74
     franco
    0.74
    ⬮
    0.74
     sidan
    0.73
    лую
    0.73
    POSITIVE LOGITS
     infestations
    0.73
     می‌توانید
    0.69
     engage
    0.62
     mutlaka
    0.61
    scapes
    0.60
     Winning
    0.60
     खी
    0.59
    কুট
    0.58
    Winning
    0.57
    stalk
    0.57
    Act Density 0.196%

    No Known Activations