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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‍♀️
    2.66
    =\{\
    2.64
    য়ে
    2.64
    !--
    2.60
    ={\
    2.57
     amide
    2.57
     crore
    2.56
    beginner
    2.54
    ый
    2.54
    =:
    2.46
    POSITIVE LOGITS
    𝐚
    2.72
    ح
    2.69
    ف
    2.68
    𝐩
    2.59
    ー
    2.56
    ব
    2.55
    t
    2.54
    ो
    2.51
    тті
    2.47
    𝐭
    2.42
    Act Density 0.063%

    No Known Activations