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

    Neuronpedia

    INDEX
    Explanations

    special formatting elements or symbols that are not standard text

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

    Text before hyphens and unusual tokens

    np_acts-logits-general · gemini-2.0-flash

    medical, technical, and foreign language content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hauptartikel
    -0.70
    loit
    -0.69
     mergeFrom
    -0.68
    rawDesc
    -0.65
    PreferredItem
    -0.64
    MockBean
    -0.59
    ragalactic
    -0.58
    Spoljašnje
    -0.56
    msgSender
    -0.56
     <=",
    -0.56
    POSITIVE LOGITS
     дописавши
    0.62
     aérea
    0.59
    oOo
    0.57
    tvguidetime
    0.57
    snip
    0.55
     خارجية
    0.53
     laiton
    0.53
    SuppressLint
    0.52
     متعلقه
    0.50
     rotors
    0.49
    Act Density 0.550%

    No Known Activations