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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to data structures and mathematical models

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

    locations and points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.48
    KommentareTeilen
    -0.48
    CreateModel
    -0.48
     nakalista
    -0.48
     TextAppearance
    -0.45
    httphttps
    -0.45
    帖最后由
    -0.44
    ByVersion
    -0.44
     ArrayAdapter
    -0.43
    XmlAccessType
    -0.43
    POSITIVE LOGITS
     navideños
    0.46
     besonder
    0.46
     stations
    0.45
     checkpoints
    0.43
     steder
    0.42
    sumowanie
    0.42
     paradas
    0.40
    站
    0.40
     intersections
    0.40
     points
    0.39
    Act Density 0.217%

    No Known Activations