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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كسب
    -0.09
    dff
    -0.08
    .backward
    -0.08
    bildung
    -0.07
    secondary
    -0.07
    Stephen
    -0.07
    debug
    -0.07
    %),
    -0.07
    ceph
    -0.07
    bbbb
    -0.07
    POSITIVE LOGITS
     Modelo
    0.07
     الجزائري
    0.07
     Aleppo
    0.07
     ilçe
    0.07
    .'↵↵
    0.07
     Investor
    0.07
     المحل
    0.07
    区
    0.07
    alo
    0.07
     стиль
    0.07
    Act Density 0.011%

    No Known Activations