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

    Neuronpedia

    INDEX
    Explanations

    Mentions years/vintages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heavyweight
    -0.07
    turnstile
    -0.06
    villa
    -0.06
     trenches
    -0.06
    奪
    -0.06
     �
    -0.06
     Mug
    -0.06
    fila
    -0.06
     denn
    -0.06
     seals
    -0.06
    POSITIVE LOGITS
    (material
    0.08
     世
    0.07
     Products
    0.07
    ωτερ
    0.06
    .rating
    0.06
     ऑ
    0.06
    _shell
    0.06
     qualify
    0.06
     ltd
    0.06
    curring
    0.06
    Act Density 0.101%

    No Known Activations