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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ellison
    -0.08
     vect
    -0.07
    	BIT
    -0.06
     embr
    -0.06
    スタ
    -0.06
    iseconds
    -0.06
     desserts
    -0.06
     Chang
    -0.06
    are
    -0.06
     ┃
    -0.06
    POSITIVE LOGITS
     tempList
    0.07
     %↵↵
    0.07
    pants
    0.07
     Internacional
    0.06
    ”。↵↵
    0.06
    Textarea
    0.06
     ",";↵
    0.06
     выпол
    0.06
     звіт
    0.06
    andi
    0.06
    Act Density 0.002%

    No Known Activations