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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	offset
    -0.06
     yavaş
    -0.06
     제
    -0.06
     mult
    -0.06
    ests
    -0.06
     Gunn
    -0.06
    nees
    -0.06
    اير
    -0.06
     pragma
    -0.06
     зб
    -0.06
    POSITIVE LOGITS
    ็กชาย
    0.07
    ีพ
    0.06
    妹
    0.06
     fleece
    0.06
    SpecWarn
    0.06
    ([]
    0.06
     Cuban
    0.06
     Sey
    0.06
    لیت
    0.06
    iced
    0.06
    Act Density 0.014%

    No Known Activations