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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Piano
    -0.07
    nad
    -0.06
    /Input
    -0.06
     advancing
    -0.06
    نام
    -0.06
    专
    -0.06
     queues
    -0.06
     impair
    -0.06
     deed
    -0.06
    يران
    -0.06
    POSITIVE LOGITS
    اعر
    0.07
    "class
    0.07
    .YELLOW
    0.07
    	cin
    0.07
    <html
    0.07
    aceutical
    0.07
     assigns
    0.07
    reur
    0.06
    elif
    0.06
     #+#
    0.06
    Act Density 0.373%

    No Known Activations