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

    Neuronpedia

    INDEX
    Explanations

    crocodile and alligator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ER
    0.79
     جميع
    0.79
     في
    0.72
     violently
    0.70
     ചില
    0.67
     guerr
    0.66
     powied
    0.65
     trebuie
    0.64
     يا
    0.63
     przypadku
    0.62
    POSITIVE LOGITS
    t
    1.22
    i
    0.88
    r
    0.77
    h
    0.73
    ร
    0.73
    '
    0.70
     on
    0.70
    ب
    0.69
    p
    0.66
    tcp
    0.66
    Act Density 0.005%

    No Known Activations