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

    Neuronpedia

    INDEX
    Explanations

    references to scientific measurements and methodologies

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

    Numbers between ten and one hundred

    np_acts-logits-general · gemini-2.0-flash

    numbers and approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.97
     الحره
    -0.85
    ViewImports
    -0.83
     виправивши
    -0.81
    rrggbb
    -0.76
    存于互联网档案馆
    -0.76
     Roskov
    -0.75
    TintMode
    -0.73
     незавершена
    -0.73
    DoubleQuotes
    -0.72
    POSITIVE LOGITS
     sixty
    1.69
     thirty
    1.66
     eighty
    1.62
     fifty
    1.61
     forty
    1.59
     seventy
    1.58
     twenty
    1.56
     ninety
    1.48
     fifteen
    1.46
     approximately
    1.45
    Act Density 3.258%

    No Known Activations