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

    Neuronpedia

    INDEX
    Explanations

    in front of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sour
    -0.07
    zt
    -0.07
    _impl
    -0.07
    .mix
    -0.07
    boru
    -0.06
     envelope
    -0.06
    počet
    -0.06
     Ul
    -0.06
     gears
    -0.06
    473
    -0.06
    POSITIVE LOGITS
     OA
    0.07
     foregoing
    0.06
     прос
    0.06
     segments
    0.06
     Elevated
    0.06
    django
    0.06
    >/
    0.06
    estr
    0.06
    FXML
    0.06
     repell
    0.06
    Act Density 0.011%

    No Known Activations