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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capitalize
    -0.08
     circuitry
    -0.08
    참
    -0.08
    haw
    -0.08
     Enhance
    -0.07
    ただ
    -0.07
     endings
    -0.07
     enclosing
    -0.07
    인의
    -0.07
    edt
    -0.07
    POSITIVE LOGITS
    _RATIO
    0.09
     ટકા
    0.08
     scaling
    0.08
    _ratio
    0.08
     प्रतिशत
    0.08
     শতাংশ
    0.08
    _percentage
    0.08
    iel
    0.08
    ERCENT
    0.08
     برابر
    0.08
    Act Density 0.037%

    No Known Activations