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

    Neuronpedia

    INDEX
    Explanations

    DB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    只见
    -0.07
    诡
    -0.07
     myths
    -0.07
    uin
    -0.07
    流感
    -0.07
    tokenId
    -0.07
    v
    -0.06
    decorators
    -0.06
    所以说
    -0.06
     CONF
    -0.06
    POSITIVE LOGITS
    .toDouble
    0.07
     ribbon
    0.07
    ertura
    0.06
    achievement
    0.06
    .entry
    0.06
    мот
    0.06
    ariance
    0.06
     embarrassment
    0.06
    -aligned
    0.06
     sola
    0.06
    Act Density 0.001%

    No Known Activations