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
    (order
    -0.07
     exceeded
    -0.07
     accompanies
    -0.07
     Сам
    -0.06
    нений
    -0.06
     pillows
    -0.06
    Сам
    -0.06
     rites
    -0.06
     byste
    -0.06
    нес
    -0.06
    POSITIVE LOGITS
    .inv
    0.08
     (?)
    0.07
     Rolling
    0.06
     "~
    0.06
     بیشتر
    0.06
     wrapping
    0.06
    .sigmoid
    0.06
    _POP
    0.06
     exposing
    0.06
    UNKNOWN
    0.06
    Act Density 0.022%

    No Known Activations