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

    Neuronpedia

    INDEX
    Explanations

    separators or punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scientifique
    -0.08
     conceal
    -0.08
     nuclé
    -0.08
     concealed
    -0.08
    pre
    -0.08
    esti
    -0.07
     ette
    -0.07
    pattern
    -0.07
     diligence
    -0.07
    stə
    -0.07
    POSITIVE LOGITS
     humanities
    0.10
     subjective
    0.10
    	GUI
    0.10
     انسانی
    0.09
     художе
    0.08
     मानव
    0.08
     মানব
    0.08
     extracurricular
    0.08
     humanas
    0.08
     softer
    0.08
    Act Density 0.300%

    No Known Activations