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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     efect
    -0.07
    一切
    -0.07
    Birth
    -0.07
     "&
    -0.07
    gross
    -0.07
    .wh
    -0.07
     gross
    -0.06
     EXPECT
    -0.06
     outweigh
    -0.06
    ằ
    -0.06
    POSITIVE LOGITS
    digit
    0.06
    alter
    0.06
     peers
    0.06
     MVP
    0.06
    .day
    0.06
    lod
    0.06
    _algorithm
    0.06
    іла
    0.06
     cellar
    0.06
     worldview
    0.06
    Act Density 0.001%

    No Known Activations