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

    Neuronpedia

    INDEX
    Explanations

    descriptions and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     انھوں
    0.45
     მათ
    0.41
    рец
    0.40
    氹
    0.39
     wreaths
    0.38
     жінок
    0.38
     urls
    0.38
     ол
    0.38
     görsel
    0.38
     обл
    0.37
    POSITIVE LOGITS
    accepted
    0.43
    t
    0.38
    lam
    0.36
    aya
    0.36
    Sub
    0.36
    eleg
    0.36
     naam
    0.36
    subprocess
    0.36
    taken
    0.35
    im
    0.35
    Act Density 0.003%

    No Known Activations