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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical sequences or identifiers related to specific contexts

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

    Japanese dialog timings in subtitles

    np_acts-logits-general · gemini-2.0-flash

    timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Xna
    -0.52
     utilisons
    -0.52
    enschap
    -0.51
     distanciation
    -0.49
    ropriate
    -0.49
     sé
    -0.49
     appropriate
    -0.47
    WebElementEntity
    -0.47
    addGap
    -0.47
     keber
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.74
    AndEndTag
    0.66
     Gilberto
    0.65
     HasFactory
    0.64
    drawSprites
    0.64
    titleMargin
    0.61
    ьаж
    0.60
     Eleventh
    0.59
    WriteBarrier
    0.58
     BrowserModule
    0.58
    Act Density 0.508%

    No Known Activations