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

    Neuronpedia

    INDEX
    Explanations

    numerical values or codes

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

    Number "twelve" in different languages/formats

    np_acts-logits-general · gemini-2.0-flash

    twelve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.68
     propOrder
    -0.66
     ISNI
    -0.64
     Thursdays
    -0.63
     Huss
    -0.63
     Bluff
    -0.61
     Thursday
    -0.59
     okuyayım
    -0.59
     tripod
    -0.58
     Jaffe
    -0.58
    POSITIVE LOGITS
              
    1.20
     twelve
    0.63
    十二
    0.61
     XII
    0.61
     Twelve
    0.60
    Twelve
    0.59
    ensen
    0.57
     Herren
    0.52
    twelve
    0.52
     ۱۲
    0.52
    Act Density 0.097%

    No Known Activations