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

    Neuronpedia

    INDEX
    Explanations

    numerical values or quantities

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

    various languages and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fla
    -0.40
     cap
    -0.40
     ple
    -0.39
    cloudflare
    -0.39
    Cap
    -0.38
     fut
    -0.38
     Harg
    -0.38
     Gou
    -0.37
     Bru
    -0.37
     descal
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.73
    Rüyada
    0.65
     okuyayım
    0.62
     '\\;'
    0.62
     للمعارف
    0.61
     Administrativna
    0.60
     متعلقه
    0.58
    :✨
    0.58
     Smarty
    0.58
    majánló
    0.58
    Act Density 0.442%

    No Known Activations