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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ResourceManager
    -0.07
    azar
    -0.07
     education
    -0.06
     elektron
    -0.06
    chemistry
    -0.06
     mnist
    -0.06
    -list
    -0.06
     склад
    -0.06
    .histogram
    -0.06
     acad
    -0.06
    POSITIVE LOGITS
    pm
    0.07
    '}>↵
    0.07
    SSION
    0.07
    (sr
    0.07
    كال
    0.06
    äs
    0.06
    	It
    0.06
    departureday
    0.06
    %;
↵
    0.06
    MSN
    0.06
    Act Density 0.056%

    No Known Activations