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

    Neuronpedia

    INDEX
    Explanations

    terminology related to cleanliness, purity, and contamination, often in a procedural or ritualistic context

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

    Follows a form of "is/are [adjective]"

    np_acts-logits-general · gemini-2.0-flash

    linking verbs followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ison
    -0.50
    FileNotFound
    -0.49
    égio
    -0.45
     yoktur
    -0.44
    ildes
    -0.44
     vnder
    -0.44
     Wikiseite
    -0.44
     initiation
    -0.43
    boc
    -0.42
    PARATION
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.91
    IVEREF
    0.85
     createSprite
    0.84
     adjective
    0.80
     dikatakan
    0.73
    Becoming
    0.72
     ***!
    0.71
    LookAnd
    0.70
     Becomes
    0.70
     بيها
    0.70
    Act Density 0.522%

    No Known Activations