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

    Neuronpedia

    INDEX
    Explanations

    code, documentation, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >>>>>>>>
    -0.08
     брос
    -0.07
     překvap
    -0.07
     flip
    -0.06
    Ч
    -0.06
    creasing
    -0.06
    doubleValue
    -0.06
     sám
    -0.06
     Biggest
    -0.06
    _txt
    -0.06
    POSITIVE LOGITS
    (reason
    0.06
    .KeyCode
    0.06
     Auburn
    0.06
    irie
    0.06
    .opens
    0.06
     çıkan
    0.06
    ')"↵
    0.06
    oti
    0.06
    	input
    0.06
     수정
    0.05
    Act Density 0.000%

    No Known Activations