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

    Neuronpedia

    INDEX
    Explanations

    Experiencing something else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [C
    -0.07
    思考
    -0.07
    where
    -0.06
     panda
    -0.06
    .closed
    -0.06
     Gö
    -0.06
    (pred
    -0.06
    inki
    -0.06
     См
    -0.06
    通知
    -0.06
    POSITIVE LOGITS
    ）は
    0.07
     تور
    0.07
    awe
    0.06
     मन
    0.06
     PureComponent
    0.06
    ])).
    0.06
    >tag
    0.06
    __;↵
    0.06
    .selectAll
    0.06
     ],↵
    0.06
    Act Density 0.021%

    No Known Activations