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

    Neuronpedia

    INDEX
    Explanations

    how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     위해
    0.35
    無線
    0.35
     abbia
    0.35
     According
    0.35
     alebo
    0.34
    的情况下
    0.34
    Մ
    0.34
    وک
    0.34
    哈哈哈
    0.34
     रहेंगी
    0.34
    POSITIVE LOGITS
    an
    0.64
    soever
    0.62
    ان
    0.61
    that
    0.48
    it
    0.47
     it
    0.47
     to
    0.47
    a
    0.47
    to
    0.43
    n
    0.41
    Act Density 0.189%

    No Known Activations