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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    multiple studies reporting findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.67
     propOrder
    -0.65
    AddTagHelper
    -0.64
     pinulongan
    -0.61
    StoryboardSegue
    -0.56
    nodoc
    -0.54
    /**
    -0.53
    ppuden
    -0.53
    AutoField
    -0.51
    RenderAtEndOf
    -0.51
    POSITIVE LOGITS
     several
    0.91
     Several
    0.89
    Several
    0.88
    several
    0.83
     plusieurs
    0.75
     Plusieurs
    0.73
     varios
    0.72
     mehrere
    0.71
    몇
    0.71
    Plusieurs
    0.69
    Act Density 0.154%

    No Known Activations