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

    Neuronpedia

    INDEX
    Explanations

    divisor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    し�
    -0.07
     Arkansas
    -0.06
     drv
    -0.06
     indent
    -0.06
     충
    -0.06
    Bear
    -0.06
     Conf
    -0.06
     conf
    -0.06
     cca
    -0.06
    CGRect
    -0.06
    POSITIVE LOGITS
    ео
    0.07
    TION
    0.07
     Beauty
    0.07
    誉
    0.07
     출시
    0.06
    ayan
    0.06
    720
    0.06
    ọi
    0.06
    REMOTE
    0.06
    ाय
    0.06
    Act Density 5.742%

    No Known Activations