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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     juice
    -0.07
     Juice
    -0.07
    ेप
    -0.07
     accommodation
    -0.07
    Pid
    -0.07
     Cunningham
    -0.06
    $_
    -0.06
    μβ
    -0.06
    efd
    -0.06
     lounge
    -0.06
    POSITIVE LOGITS
     потрібно
    0.07
     خودش
    0.07
    (Canvas
    0.07
    ({
↵
    0.06
     громад
    0.06
     другими
    0.06
     (:
    0.06
    	parse
    0.06
    есь
    0.06
    (Expected
    0.06
    Act Density 0.037%

    No Known Activations