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

    Neuronpedia

    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    φο
    -0.07
     vocabulary
    -0.07
     Б
    -0.06
     回
    -0.06
    еріга
    -0.06
    River
    -0.06
    jQuery
    -0.06
     gratitude
    -0.06
     日
    -0.06
    	friend
    -0.06
    POSITIVE LOGITS
    .timestamp
    0.07
     خصوص
    0.07
     vd
    0.07
    _MARGIN
    0.06
     Historic
    0.06
     vac
    0.06
     Ac
    0.06
     فقط
    0.06
     önemlidir
    0.06
    SQLException
    0.06
    Act Density 0.003%

    No Known Activations