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

    Neuronpedia

    INDEX
    Explanations

    http, about, urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗬
    0.67
    しば
    0.63
    ряду
    0.58
    𝗥
    0.56
    完毕
    0.56
     sceGu
    0.56
     impuestos
    0.55
    之路
    0.55
    𝗚
    0.55
     fertilization
    0.55
    POSITIVE LOGITS
    is
    0.71
    ing
    0.59
    oi
    0.56
    ți
    0.54
    ć
    0.54
    c
    0.52
    bereich
    0.52
    in
    0.51
    est
    0.51
    fficient
    0.51
    Act Density 0.028%

    No Known Activations