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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dragging
    -0.06
    选择
    -0.06
     Automatic
    -0.06
     engineering
    -0.06
     badge
    -0.06
    Sorted
    -0.06
    _swap
    -0.06
     merged
    -0.06
     verification
    -0.06
     affairs
    -0.06
    POSITIVE LOGITS
    <>(
    0.07
     Magnus
    0.07
     분
    0.06
     Lair
    0.06
    802
    0.06
    (ss
    0.06
    риф
    0.06
     outreach
    0.06
     Listed
    0.06
     بودن
    0.06
    Act Density 0.006%

    No Known Activations