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

    Neuronpedia

    INDEX
    Explanations

    Mi, Ni, Bu, Nu, ru prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     апреле
    0.41
    淤
    0.41
    ÍC
    0.39
    혀
    0.39
    онов
    0.39
    ಯ
    0.39
    othiaz
    0.38
    க்
    0.38
    ⬯
    0.38
     అవ
    0.37
    POSITIVE LOGITS
    pper
    0.77
    pping
    0.71
    pped
    0.64
    ppy
    0.63
    ffi
    0.63
    ff
    0.63
    xt
    0.61
    ppers
    0.60
    ppling
    0.59
    ppo
    0.58
    Act Density 0.039%

    No Known Activations