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

    Neuronpedia

    INDEX
    Explanations

    car redesigns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    標準
    -0.06
     Federation
    -0.06
     boca
    -0.06
    	doc
    -0.06
    opacity
    -0.06
    toHaveBeenCalledWith
    -0.06
    366
    -0.06
     sensed
    -0.06
    uarios
    -0.06
    減
    -0.06
    POSITIVE LOGITS
    .TRAILING
    0.08
     assort
    0.07
     kre
    0.07
    ，该
    0.07
    ategor
    0.06
    EMPLATE
    0.06
    	ui
    0.06
     Malone
    0.06
    [float
    0.06
     fortunes
    0.06
    Act Density 0.027%

    No Known Activations