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

    Neuronpedia

    INDEX
    Explanations

    appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	class
    -0.07
     clustered
    -0.07
     Converter
    -0.06
    ält
    -0.06
     Hag
    -0.06
    ギ
    -0.06
    style
    -0.06
     AAA
    -0.06
    eo
    -0.06
    的人
    -0.06
    POSITIVE LOGITS
    luv
    0.07
     ms
    0.07
    _inp
    0.07
     верес
    0.06
    _READONLY
    0.06
     ___
    0.06
     sufferers
    0.06
     CART
    0.06
     lø
    0.06
    +='<
    0.06
    Act Density 0.045%

    No Known Activations