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

    Neuronpedia

    INDEX
    Explanations

    function definitions and method invocations in code

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

    return false; })

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -1.18
     queſta
    -1.16
    niſſe
    -1.11
     Administrativna
    -1.11
    ſchaft
    -1.09
     Италијани
    -1.09
     autorytatywna
    -1.08
     surla
    -1.07
    iſchen
    -1.05
    ésultats
    -1.04
    POSITIVE LOGITS
    ↵↵
    0.68
    .
    0.49
     
    0.49
    <eos>
    0.46
    }
    0.45
     the
    0.44
     and
    0.44
    ↵
    0.44
     of
    0.43
    </table>
    0.41
    Act Density 0.007%

    No Known Activations