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

    Neuronpedia

    INDEX
    Explanations

    occurrences of asterisks or their variations used in code or mathematical contexts

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.73
     normaux
    -0.48
    CreateModel
    -0.44
     arché
    -0.44
     pleaſure
    -0.44
    antaranya
    -0.43
     Zapata
    -0.43
    erçe
    -0.42
    ionales
    -0.42
     africains
    -0.41
    POSITIVE LOGITS
    **
    1.62
     **
    1.46
    **)
    1.21
     **)
    1.20
    .**
    1.15
    **,
    1.15
    ,**
    1.13
    )**
    1.11
    **.
    1.10
    **(
    1.05
    Act Density 0.015%

    No Known Activations