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

    Neuronpedia

    INDEX
    Explanations

    mathematical identifiers and symbols commonly found in equations

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

    Mathematical expressions/symbols

    np_acts-logits-general · gemini-2.0-flash

    latex math fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.58
    @
    -0.58
     />';
    -0.57
    "',
    -0.56
     Perrin
    -0.56
    ยว
    -0.54
    )!
    -0.53
    *@
    -0.52
    "]:
    -0.52
    )]:
    -0.50
    POSITIVE LOGITS
    {\
    1.65
     {\
    1.46
    ){\
    1.31
     ${\
    1.17
    ]{\
    1.09
    ${\
    1.07
    ,{\
    1.04
    ({\
    1.02
    {{\
    1.01
    }{\
    0.99
    Act Density 0.909%

    No Known Activations