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

    Neuronpedia

    INDEX
    Explanations

    wiki markup and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    absolutely
    0.46
    Absolutely
    0.41
    ciples
    0.41
     ছেড়ে
    0.40
     teamTable
    0.40
    thren
    0.40
    openjdk
    0.39
    CameraController
    0.38
    auern
    0.38
    seekBar
    0.38
    POSITIVE LOGITS
     LINK
    0.58
     link
    0.57
     {{
    0.57
     parameter
    0.55
     Parameter
    0.55
     Link
    0.54
     Wikidata
    0.54
     {{{
    0.53
     링크
    0.52
     Lua
    0.51
    Act Density 0.002%

    No Known Activations