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

    Neuronpedia

    INDEX
    Explanations

    html head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     уйнау
    0.64
    لسل
    0.61
     машинасы
    0.61
     уйнарга
    0.61
    لنا
    0.59
    SXml
    0.59
    Bracelet
    0.58
    Dollars
    0.58
    }=\
    0.57
    اويه
    0.57
    POSITIVE LOGITS
    in
    1.04
    n
    0.88
    em
    0.79
    ın
    0.76
    th
    0.74
    re
    0.74
    the
    0.73
    ul
    0.72
    im
    0.70
    te
    0.70
    Act Density 0.031%

    No Known Activations