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

    Neuronpedia

    INDEX
    Explanations

    Yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insanely
    -0.07
    emaakt
    -0.07
    增长
    -0.07
    	Use
    -0.07
     View
    -0.07
     бізнес
    -0.06
     obtain
    -0.06
     DT
    -0.06
    Transpose
    -0.06
     QUERY
    -0.06
    POSITIVE LOGITS
    _GP
    0.07
    زي
    0.06
     sexism
    0.06
     اصول
    0.06
    seg
    0.06
     düşman
    0.06
    AMED
    0.06
     움
    0.06
     başarılı
    0.06
     вов
    0.06
    Act Density 0.010%

    No Known Activations