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

    Neuronpedia

    INDEX
    Explanations

    strings that include numerical values or specific formatting characters

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

    file path segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activités
    -0.36
    明
    -0.35
    チール
    -0.35
     function
    -0.33
     once
    -0.32
     libremente
    -0.32
     slowly
    -0.32
    function
    -0.32
     lentamente
    -0.32
     continuamente
    -0.32
    POSITIVE LOGITS
    ніципалі
    0.79
    Datuak
    0.71
     مشين
    0.71
    出版年
    0.69
    hoeddwyd
    0.66
     kasarigan
    0.66
    ंदीखरीदारी
    0.65
    Personensuche
    0.64
     الرياضيه
    0.60
    rungsseite
    0.60
    Act Density 0.000%

    No Known Activations