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

    Neuronpedia

    INDEX
    Explanations

    actors and films

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стен
    -0.07
    وير
    -0.06
    CNT
    -0.06
    ौत
    -0.06
     ateş
    -0.06
     seemingly
    -0.06
    소개
    -0.06
    stoupil
    -0.06
    Inside
    -0.06
     Hak
    -0.06
    POSITIVE LOGITS
    educt
    0.07
    aji
    0.07
    ysis
    0.06
    (fill
    0.06
    azor
    0.06
     Lucas
    0.06
    __);↵↵
    0.06
    νει
    0.06
     MODULE
    0.06
    .tile
    0.06
    Act Density 0.006%

    No Known Activations