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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тради
    -0.07
     hurl
    -0.07
     injured
    -0.06
     mũi
    -0.06
    ука
    -0.06
    ующих
    -0.06
    (Student
    -0.06
    files
    -0.06
    	report
    -0.06
     utter
    -0.06
    POSITIVE LOGITS
    кам
    0.06
    feito
    0.06
    ypi
    0.06
     zeit
    0.06
     практически
    0.06
    )();↵
    0.06
    urities
    0.06
    _nr
    0.06
     مس
    0.06
     Mono
    0.05
    Act Density 0.048%

    No Known Activations