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

    Neuronpedia

    INDEX
    Explanations

    guess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outlining
    -0.09
    outline
    -0.09
    nam
    -0.08
    Outline
    -0.08
    ensky
    -0.08
     parcours
    -0.07
    يوت
    -0.07
     namely
    -0.07
     ван
    -0.07
     grain
    -0.07
    POSITIVE LOGITS
     specifics
    0.09
    (ext
    0.09
     ext
    0.09
     reliably
    0.08
     without
    0.08
     fácilmente
    0.08
     بسهولة
    0.08
     extent
    0.08
     perfectly
    0.08
     בלי
    0.08
    Act Density 0.022%

    No Known Activations