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

    Neuronpedia

    INDEX
    Explanations

    references to figures, tables, and equations in a document

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

    [Figure] citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⤹
    -0.57
     informée
    -0.42
    \{\\
    -0.41
     Catawiki
    -0.40
     Lombardi
    -0.40
    </table>
    -0.40
     exposiciones
    -0.38
     klimat
    -0.38
    ]")]
    -0.38
    ))/(
    -0.37
    POSITIVE LOGITS
     [
    0.63
    httphttps
    0.59
    @[+][
    0.54
     ["
    0.54
    verwijspagina
    0.54
     ["",
    0.53
     [$
    0.53
     $[
    0.52
    anskrit
    0.51
    [-\
    0.51
    Act Density 1.499%

    No Known Activations