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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical properties and theorems in probability

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

    almost surely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.52
     &___
    -0.51
    PostInfinity
    -0.48
    RenderAtEndOf
    -0.45
     Réponses
    -0.41
     betweenstory
    -0.41
    rrggbb
    -0.40
    AccessorTable
    -0.40
    ppuden
    -0.39
     Exactos
    -0.39
    POSITIVE LOGITS
     measure
    0.77
    measure
    0.74
    Measure
    0.71
     almost
    0.70
     Measure
    0.68
     MEASURE
    0.66
    almost
    0.64
     Almost
    0.61
     measurable
    0.61
     quase
    0.60
    Act Density 0.909%

    No Known Activations