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

    Neuronpedia

    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     단
    -0.07
     lassen
    -0.07
    pars
    -0.07
     شعر
    -0.06
    paper
    -0.06
    iazza
    -0.06
     Riyadh
    -0.06
     Haus
    -0.06
     Pav
    -0.06
    :@{
    -0.06
    POSITIVE LOGITS
    ционные
    0.07
     pitching
    0.07
    aciones
    0.07
     lake
    0.06
    �
    0.06
     slopes
    0.06
     seizing
    0.06
    UTION
    0.06
     vibrations
    0.06
    яд
    0.06
    Act Density 0.008%

    No Known Activations