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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SKTOP
    -0.06
    /Image
    -0.06
     usu
    -0.06
    harma
    -0.06
    	W
    -0.06
    amba
    -0.06
     LW
    -0.06
     لغ
    -0.06
     germ
    -0.06
    ENG
    -0.05
    POSITIVE LOGITS
     propiedad
    0.07
     olmadan
    0.07
     journalist
    0.07
    getElement
    0.06
     Richie
    0.06
     см
    0.06
     Shirt
    0.06
     Intelligence
    0.06
    بات
    0.06
    .Encoding
    0.06
    Act Density 0.002%

    No Known Activations