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

    Neuronpedia

    INDEX
    Explanations

    numerical figures and statistical results in research contexts

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

    Percentages in parentheses

    np_acts-logits-general · gemini-2.0-flash

    percentages followed by symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "));
    -1.07
    ));
    -1.07
     "));
    -1.06
    ));
    -1.04
    "));
    -1.04
    '));
    -1.03
     );
    -1.02
     ");
    -1.00
     });
    -1.00
     );
    -1.00
    POSITIVE LOGITS
     تضيفلها
    0.73
     autorytatywna
    0.71
     وتسجيلات
    0.61
     adulte
    0.58
    zzleHttp
    0.58
     inoxid
    0.57
    ())
    0.57
    octanol
    0.55
     افتراض
    0.55
     الحره
    0.55
    Act Density 0.617%

    No Known Activations