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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Score
    -0.07
    Kyle
    -0.07
     subtraction
    -0.07
     Plants
    -0.07
     fibers
    -0.07
     adapting
    -0.07
     plants
    -0.07
     gmail
    -0.07
     critiques
    -0.07
     Karma
    -0.07
    POSITIVE LOGITS
    ̣
    0.06
    _Selected
    0.06
    euillez
    0.06
    níkem
    0.06
    тю
    0.06
    	typedef
    0.06
     Tại
    0.06
     H�
    0.06
     Král
    0.06
    ?action
    0.06
    Act Density 0.005%

    No Known Activations