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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pew
    -0.07
    appiness
    -0.07
    _old
    -0.06
    Mem
    -0.06
     الأف
    -0.06
    .remaining
    -0.06
    chmod
    -0.06
     epit
    -0.06
    _corr
    -0.06
     дых
    -0.06
    POSITIVE LOGITS
    ’ll
    0.07
    veal
    0.07
    -g
    0.06
    sterreich
    0.06
    슈
    0.06
    (register
    0.06
     معل
    0.06
     безпеки
    0.06
    graphic
    0.06
    keepers
    0.06
    Act Density 0.001%

    No Known Activations