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

    Neuronpedia

    INDEX
    Explanations

    formatting related to mathematical expressions and equations

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

    mathematical alignment blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.78
     ſind
    -0.77
    niſſe
    -0.73
    -0.73
     iſt
    -0.68
     ſeine
    -0.67
     ſein
    -0.66
     ſans
    -0.66
     ſeinen
    -0.66
    tvguidetime
    -0.66
    POSITIVE LOGITS
    </>
    0.73
    </tfoot>
    0.47
    </>
    0.40
    toByteArray
    0.36
    endregion
    0.36
     idéia
    0.35
    ChildScrollView
    0.35
    ⎦
    0.32
     ...
    0.31
     */
    0.29
    Act Density 0.003%

    No Known Activations