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

    Neuronpedia

    INDEX
    Explanations

    heart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     control
    -0.07
     better
    -0.07
     alley
    -0.07
    -loading
    -0.06
    露出
    -0.06
     quieter
    -0.06
     знать
    -0.06
    /issues
    -0.06
    くる
    -0.05
     func
    -0.05
    POSITIVE LOGITS
    Banner
    0.07
     contentious
    0.07
    [X
    0.07
     pagina
    0.06
    Council
    0.06
    Basket
    0.06
    <SpriteRenderer
    0.06
    OfDay
    0.06
     незалеж
    0.06
     Ministers
    0.06
    Act Density 0.004%

    No Known Activations