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

    Neuronpedia

    INDEX
    Explanations

    Equations and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cou
    -0.08
    充
    -0.07
    ورة
    -0.06
     LEDs
    -0.06
    овани
    -0.06
    lers
    -0.06
     resent
    -0.06
     numer
    -0.06
     Ps
    -0.06
    анню
    -0.06
    POSITIVE LOGITS
    сім
    0.07
    creens
    0.06
    tility
    0.06
    >About
    0.06
    recio
    0.06
     微
    0.06
    roupon
    0.06
    liga
    0.06
    ００
    0.06
    №
    0.06
    Act Density 0.015%

    No Known Activations