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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     rond
    -0.07
    _closed
    -0.07
     zach
    -0.07
    (SQL
    -0.07
     mann
    -0.06
    :before
    -0.06
    .assertRaises
    -0.06
     marrying
    -0.06
     Minneapolis
    -0.06
    POSITIVE LOGITS
    ETweet
    0.06
    ưng
    0.06
     viewpoints
    0.06
    conda
    0.06
    staw
    0.06
    xEB
    0.06
    体
    0.06
    fas
    0.06
     shipping
    0.06
    landing
    0.06
    Act Density 0.000%

    No Known Activations