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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	change
    -0.07
     ByVal
    -0.06
     =",
    -0.06
    -0.06
     dar
    -0.06
     ภาษ
    -0.06
    	verify
    -0.06
    пи
    -0.06
    scoped
    -0.06
    	public
    -0.06
    POSITIVE LOGITS
    보고
    0.07
    ач
    0.07
     Weinstein
    0.06
    checkpoint
    0.06
     Tea
    0.06
     bağlantı
    0.06
     prostitu
    0.06
    611
    0.06
     Massachusetts
    0.06
     외
    0.06
    Act Density 0.000%

    No Known Activations