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

    Neuronpedia

    INDEX
    Explanations

    variables and operators associated with mathematical and computational expressions

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

    mathematical expressions with exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.54
    "]);
    -0.47
     ویکی‌پدی
    -0.45
     gyhoeddwyd
    -0.44
     '\\;'
    -0.44
    сылкі
    -0.43
     فہرست
    -0.43
    تقاوى
    -0.43
    Hozzáférés
    -0.42
     hornear
    -0.42
    POSITIVE LOGITS
    MarshalTo
    0.40
    parsedMessage
    0.37
    EndContext
    0.37
     disponibilités
    0.35
    Ἁ
    0.35
     entière
    0.35
    ต่อ
    0.35
    UnknownFieldSet
    0.34
     Bewußt
    0.34
    nościo
    0.33
    Act Density 0.226%

    No Known Activations