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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ़ा
    -0.07
     =(
    -0.07
     '${
    -0.07
     이야
    -0.06
    數
    -0.06
    ً،
    -0.06
    _pot
    -0.06
    _SINGLE
    -0.06
     artisans
    -0.06
     řadu
    -0.06
    POSITIVE LOGITS
     اصول
    0.08
     Gib
    0.06
    abella
    0.06
    dex
    0.06
     göl
    0.06
     survival
    0.06
    ленный
    0.06
     Al
    0.06
     гір
    0.06
     creations
    0.06
    Act Density 0.000%

    No Known Activations