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

    Neuronpedia

    INDEX
    Explanations

    fitness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    عي
    0.80
     étudi
    0.80
    CHARLES
    0.79
    0.78
    С
    0.78
    $+
    0.77
    Y
    0.76
    Đi
    0.75
    З
    0.75
     effectu
    0.75
    POSITIVE LOGITS
     fitness
    1.09
    ↵↵
    1.09
    ↵
    0.99
    ak
    0.90
     fit
    0.89
    다
    0.88
     Fitness
    0.87
    و
    0.87
    ying
    0.80
    ine
    0.79
    Act Density 0.007%

    No Known Activations