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

    Neuronpedia

    INDEX
    Explanations

    Test questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tableLayoutPanel
    -0.07
    ona
    -0.07
    ám
    -0.07
     part
    -0.07
     kö
    -0.07
     te
    -0.06
    mf
    -0.06
    	mask
    -0.06
     Ap
    -0.06
    Tu
    -0.06
    POSITIVE LOGITS
    鲏
    0.08
     Hicks
    0.07
     Africans
    0.07
     ">"
    0.07
    街区
    0.07
    references
    0.07
    _THREADS
    0.07
    كيف
    0.07
    _goals
    0.07
     Manga
    0.07
    Act Density 0.003%

    No Known Activations