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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _close
    -0.07
    .so
    -0.07
     unle
    -0.06
    .setVisible
    -0.06
     Maul
    -0.06
     @@
    -0.06
     convened
    -0.06
    hooks
    -0.06
     Behavioral
    -0.06
     Analysis
    -0.06
    POSITIVE LOGITS
     Kin
    0.07
     说
    0.06
    UITableView
    0.06
    ussia
    0.06
     серьез
    0.06
    竞
    0.06
    ิบ
    0.06
     버
    0.06
     gerek
    0.06
     impressive
    0.06
    Act Density 0.024%

    No Known Activations