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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oslo
    -0.07
    ্
    -0.06
     بزر
    -0.06
    데
    -0.06
     partnering
    -0.06
     Scho
    -0.06
     说
    -0.06
    ابت
    -0.06
    	score
    -0.06
     Holidays
    -0.06
    POSITIVE LOGITS
     passionately
    0.08
     ucfirst
    0.06
    October
    0.06
     ресурс
    0.06
    ús
    0.06
     lyn
    0.06
     nên
    0.06
    matter
    0.06
    薬
    0.06
    _WARN
    0.06
    Act Density 0.027%

    No Known Activations