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

    Neuronpedia

    INDEX
    Explanations

    numerical data or references to quantities

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

    http URLs or email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
    GEBURTSDATUM
    -0.71
     informée
    -0.71
    bootstrapcdn
    -0.69
    NameInMap
    -0.69
     GenerationType
    -0.69
    Vidite
    -0.65
    -0.64
    ArgumentParser
    -0.64
     صوتيه
    -0.64
    POSITIVE LOGITS
     Heroic
    0.33
     depar
    0.29
    　　
    0.28
     ler
    0.28
     par
    0.27
    </
    0.27
     verdo
    0.27
     auto
    0.27
    uses
    0.26
     Sheriff
    0.26
    Act Density 0.002%

    No Known Activations