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

    Neuronpedia

    INDEX
    Explanations

    code lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vrouw
    -0.07
     Sapphire
    -0.07
    .Caption
    -0.06
     Challenges
    -0.06
     wake
    -0.06
    WATCH
    -0.06
     centroids
    -0.06
    strcmp
    -0.06
     cherish
    -0.06
    }'.
    -0.06
    POSITIVE LOGITS
    арат
    0.07
     модель
    0.07
     пят
    0.06
    άν
    0.06
     poj
    0.06
    owanie
    0.06
     анализ
    0.06
    eno
    0.06
     샤
    0.06
     ApplicationController
    0.06
    Act Density 0.042%

    No Known Activations