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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    genus
    -0.07
     width
    -0.06
    (
↵
    -0.06
     rarity
    -0.06
    .repeat
    -0.06
    _SAVE
    -0.06
    _err
    -0.06
    Wonder
    -0.06
    屋
    -0.06
     please
    -0.06
    POSITIVE LOGITS
    RequiredMixin
    0.07
     úč
    0.06
    осред
    0.06
     compte
    0.06
    CTR
    0.06
     squ
    0.06
    "Oh
    0.06
     běž
    0.06
    óz
    0.06
     impe
    0.06
    Act Density 0.009%

    No Known Activations