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

    Neuronpedia

    INDEX
    Explanations

    titles and names related to media and entertainment

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

    following titles/names

    np_acts-logits-general · gemini-2.0-flash

    film titles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.56
     Dunham
    -0.52
     typelib
    -0.47
     research
    -0.46
     user
    -0.44
     brukt
    -0.43
    snprintf
    -0.43
     notizia
    -0.43
     Brute
    -0.42
    ранее
    -0.42
    POSITIVE LOGITS
    ]--;
    0.75
    MemoryWarning
    0.67
    ConverterFactory
    0.60
    abestanden
    0.59
    golden
    0.57
     golden
    0.56
    sterious
    0.56
    mask
    0.56
    Eloquent
    0.53
    Golden
    0.52
    Act Density 0.165%

    No Known Activations