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

    Neuronpedia

    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scope
    -0.07
    culture
    -0.07
     ---
    -0.06
    AS
    -0.06
     fucking
    -0.06
    から
    -0.06
     erased
    -0.06
    getProperty
    -0.06
    라고
    -0.06
     кораб
    -0.06
    POSITIVE LOGITS
    attach
    0.07
     Ezek
    0.07
    �
    0.07
    frac
    0.06
    /Grid
    0.06
    Hang
    0.06
    	Test
    0.06
     सम
    0.06
     Boom
    0.06
     믿
    0.06
    Act Density 0.019%

    No Known Activations