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

    Neuronpedia

    INDEX
    Explanations

    business contexts and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    0.64
     a
    0.59
    म
    0.56
    в
    0.55
     an
    0.55
    م
    0.55
    UD
    0.53
    Thanks
    0.52
     not
    0.52
    ب
    0.52
    POSITIVE LOGITS
    präsident
    0.50
    \,.
    0.49
    ष्‍ट
    0.48
     mellitus
    0.48
     stipulates
    0.48
    كمة
    0.48
    原始内容存档于
    0.47
     conjectured
    0.47
    :‏
    0.47
     wikipagina
    0.46
    Act Density 0.000%

    No Known Activations