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

    Neuronpedia

    INDEX
    Explanations

    not Lint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PanelVisual
    0.61
     وړاندوینې
    0.50
    splitLength
    0.50
    суз
    0.50
     ഉപകരണ
    0.49
    甙
    0.49
     কমিশন
    0.47
     የታ
    0.46
     සඳ
    0.46
    ಳೆ
    0.45
    POSITIVE LOGITS
    <b>
    0.50
    s
    0.50
    <i>
    0.47
    Met
    0.47
    blog
    0.46
    My
    0.45
    met
    0.45
     Trojans
    0.45
    example
    0.44
    ecos
    0.44
    Act Density 0.006%

    No Known Activations