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

    Neuronpedia

    INDEX
    Explanations

    computer vision, neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     written
    -0.10
     technician
    -0.08
    據
    -0.07
    _written
    -0.07
     EEPROM
    -0.07
     governed
    -0.07
     mouse
    -0.07
    书
    -0.07
     remnants
    -0.07
    Written
    -0.07
    POSITIVE LOGITS
     diversified
    0.09
    扩大
    0.09
     donut
    0.08
    NULL
    0.08
     روب
    0.08
    Interstitial
    0.08
     مربع
    0.08
    =NULL
    0.08
    _quad
    0.08
    elong
    0.08
    Act Density 0.002%

    No Known Activations