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

    Neuronpedia

    INDEX
    Explanations

    references to scientific measurements and parameters

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

    "(" in scientific contexts

    np_acts-logits-general · gemini-2.0-flash

    words after parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的其他
    -0.44
     dalších
    -0.41
     heller
    -0.40
     sorpresas
    -0.40
     otros
    -0.39
     otras
    -0.39
    其他
    -0.39
     other
    -0.38
     diğer
    -0.36
     autrement
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.75
    تقاوى
    0.68
     Monfieur
    0.57
    ViewImports
    0.55
    还好
    0.54
     للاسماء
    0.54
     وتسجيلات
    0.54
    GEBURTS
    0.51
    Хьажоргаш
    0.50
     einerseits
    0.50
    Act Density 1.510%

    No Known Activations