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

    Neuronpedia

    INDEX
    Explanations

    various forms of numerical and statistical data

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

    instructions or suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -1.20
    出版年
    -1.07
    ロウィン
    -1.07
    ientras
    -1.02
    IsMutable
    -1.02
    RenderAtEndOf
    -1.01
     ſind
    -1.00
    хьтан
    -0.96
    setVerticalGroup
    -0.94
    تقاوى
    -0.94
    POSITIVE LOGITS
    _
    0.55
    By
    0.47
    DJ
    0.47
    I
    0.43
    (
    0.40
    BY
    0.40
    The
    0.40
    Y
    0.39
    DG
    0.38
    No
    0.38
    Act Density 0.018%

    No Known Activations