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

    Neuronpedia

    INDEX
    Explanations

    Analyzing user prompts / typos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Somos
    -0.09
    ادرات
    -0.08
     لجنة
    -0.08
     Opposition
    -0.08
     المخت
    -0.08
     préalable
    -0.08
     klus
    -0.08
     ביק
    -0.08
     الأعمال
    -0.08
     الرو
    -0.08
    POSITIVE LOGITS
     typo
    0.08
     sloppy
    0.08
     corrected
    0.08
     spelling
    0.08
     grammatical
    0.08
    ̌
    0.07
    sic
    0.07
     miss
    0.07
     spelled
    0.07
     বান
    0.07
    Act Density 0.079%

    No Known Activations