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

    Neuronpedia

    INDEX
    Explanations

    speech requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swept
    -0.10
     sweeping
    -0.08
     jt
    -0.08
     olt
    -0.08
     ಭ
    -0.08
     توسعه
    -0.08
    /report
    -0.08
     обнаруж
    -0.08
     ನೇ
    -0.08
     LT
    -0.07
    POSITIVE LOGITS
     punctuation
    0.08
     chast
    0.08
     caráter
    0.08
     dispenser
    0.08
     vowel
    0.07
     roulette
    0.07
    keypress
    0.07
     estética
    0.07
    roulette
    0.07
    字符
    0.07
    Act Density 0.030%

    No Known Activations