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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Almost
    -0.07
    appen
    -0.07
    lesen
    -0.07
    ому
    -0.07
    全域旅游
    -0.07
     Reception
    -0.07
    they
    -0.07
    痓
    -0.07
    อบรม
    -0.07
    öl
    -0.07
    POSITIVE LOGITS
     dan
    0.07
    玩家
    0.07
    ="$(
    0.07
    	namespace
    0.07
    ('
    0.06
    ?('
    0.06
    였다
    0.06
     engines
    0.06
     cler
    0.06
    没有必要
    0.06
    Act Density 0.055%

    No Known Activations