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

    Neuronpedia

    INDEX
    Explanations

    andes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notebooks
    -0.07
    视觉
    -0.07
     pivotal
    -0.07
     Generates
    -0.07
     oval
    -0.07
    审议
    -0.06
    _pay
    -0.06
     RTE
    -0.06
    ité
    -0.06
     ada
    -0.06
    POSITIVE LOGITS
    Fast
    0.09
    张某
    0.08
    .Position
    0.08
     princess
    0.08
    二手车
    0.08
     analytic
    0.07
    ↵	↵
    0.07
    uch
    0.07
    Michael
    0.07
     individuals
    0.07
    Act Density 0.001%

    No Known Activations