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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?=
    -0.06
     embry
    -0.06
     crack
    -0.06
    icast
    -0.06
    ui
    -0.06
    elerine
    -0.06
     blí
    -0.06
    	sys
    -0.06
    36
    -0.06
     perman
    -0.06
    POSITIVE LOGITS
    tm
    0.06
    тів
    0.06
    дат
    0.06
    чень
    0.06
    ubre
    0.06
    Orange
    0.06
     عشر
    0.06
    _we
    0.06
     Haz
    0.06
    (edit
    0.06
    Act Density 0.019%

    No Known Activations