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

    Neuronpedia

    INDEX
    Explanations

    references to ancient history and significant cultural concepts

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

    inherent rules, overall strength, relatively small

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.55
     stanga
    -0.52
    transQ
    -0.50
    bets
    -0.49
    featureID
    -0.48
    uesia
    -0.48
    blings
    -0.46
    ágenes
    -0.46
    httphttps
    -0.46
    almo
    -0.46
    POSITIVE LOGITS
    ISupport
    0.48
    {}/
    0.41
     []:
    0.41
     declaratory
    0.41
    
    0.38
    */].
    0.38
     发表于
    0.36
    (",",
    0.36
    indd
    0.36
     experimental
    0.35
    Act Density 0.020%

    No Known Activations