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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :↵↵↵↵↵↵
    -0.07
    명의
    -0.06
    (rec
    -0.06
    COVID
    -0.06
     côt
    -0.06
     les
    -0.06
     질
    -0.06
     себя
    -0.06
    (LOG
    -0.06
     lyrics
    -0.06
    POSITIVE LOGITS
    Module
    0.07
    GAME
    0.07
    Activation
    0.07
    .Inv
    0.06
    enha
    0.06
    .getInput
    0.06
    km
    0.06
     Exc
    0.06
     waive
    0.06
    cp
    0.06
    Act Density 0.015%

    No Known Activations