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

    Neuronpedia

    INDEX
    Explanations

    spaces or delimiters between words or tokens

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

    numbers and coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.66
    HomeAsUpEnabled
    -0.61
    الحياه
    -0.61
     Wikispecies
    -0.59
    MLLoader
    -0.57
    Geplaatst
    -0.57
    mappedBy
    -0.57
    يميديا
    -0.55
    URLException
    -0.54
    outWeight
    -0.54
    POSITIVE LOGITS
    <bos>
    0.77
     
    0.50
    Fos
    0.49
     
    0.47
     ​​
    0.47
     s
    0.47
     indipendente
    0.45
    McC
    0.45
    fcntl
    0.45
     engraçadas
    0.44
    Act Density 0.059%

    No Known Activations