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

    Neuronpedia

    INDEX
    Explanations

    references to control or governance in a technical or formal context

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

    Mathematical or code-related expressions/symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical formula coefficients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -1.19
    Geplaatst
    -1.08
     ویکی‌پدیا
    -1.08
     Audiodateien
    -1.01
    存于互联网档案馆
    -1.01
     bezeichneter
    -0.99
    setVerticalGroup
    -0.98
     للاسماء
    -0.98
    Portale
    -0.97
    UserScript
    -0.96
    POSITIVE LOGITS
    <bos>
    0.70
    N
    0.62
    M
    0.62
     D
    0.60
    C
    0.59
    ?
    0.59
    H
    0.59
     N
    0.58
    K
    0.58
    。
    0.57
    Act Density 0.701%

    No Known Activations