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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ière
    -0.28
     summaries
    -0.26
    津贴
    -0.26
    ucht
    -0.26
     compliments
    -0.25
    åŃ¦æľŁ
    -0.25
    æľ¬ä¹¦
    -0.25
    зд
    -0.25
    _subject
    -0.25
    _accessor
    -0.25
    POSITIVE LOGITS
    itary
    0.29
    -bars
    0.29
    åĪ«äººçļĦ
    0.28
    ä¸ĢåĪĨéĴŁ
    0.28
    https
    0.27
    许
    0.26
     ali
    0.26
     Mechan
    0.25
    线ä¸Ĭ线ä¸ĭ
    0.25
     Honolulu
    0.25
    Act Density 0.062%

    No Known Activations