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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their academic credentials or contributions in a scientific context

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

    Words/symbols found within code or equations

    np_acts-logits-general · gemini-2.0-flash

    foreign language titles and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.70
    AndEndTag
    -0.70
    Jeografia
    -0.56
    ніципалі
    -0.56
     ostavi
    -0.55
    حياتها
    -0.55
    )))));
    -0.52
    Посилання
    -0.51
    ArgsConstructor
    -0.50
    forChild
    -0.50
    POSITIVE LOGITS
    Välislingid
    0.47
     varandra
    0.47
     rõ
    0.46
     préfé
    0.45
     peaks
    0.45
     seal
    0.45
     współpracy
    0.44
     eel
    0.43
     stället
    0.42
    itesse
    0.41
    Act Density 0.062%

    No Known Activations