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

    Neuronpedia

    INDEX
    Explanations

    lora, Terracotta Army, code, columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nt
    0.43
    ገል
    0.42
    ctu
    0.40
    सूस
    0.39
    Associated
    0.39
    난다
    0.39
    ಸ
    0.39
    nk
    0.38
    ankt
    0.38
    误
    0.38
    POSITIVE LOGITS
     impunity
    0.50
     parac
    0.44
     sharp
    0.42
     கூடிய
    0.41
     wherein
    0.40
    赜
    0.39
     enim
    0.39
     código
    0.38
     unsh
    0.38
     ひ
    0.38
    Act Density 0.000%

    No Known Activations