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

    Neuronpedia

    INDEX
    Explanations

    references to external websites and their credibility

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

    chat questions and statements

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects URL and web-domain fragments (parts of web addresses and links).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.46
     näytte
    -0.44
     Wikiseite
    -0.43
     growing
    -0.42
     técn
    -0.41
     embarazadas
    -0.41
     monasterio
    -0.41
     régime
    -0.40
     invitaciones
    -0.40
    tapeta
    -0.39
    POSITIVE LOGITS
     שוליים
    0.54
    tvguidetime
    0.50
    astify
    0.49
    featureID
    0.47
    tagHelperRunner
    0.46
     Roskov
    0.44
     consultato
    0.44
    findpost
    0.41
    MemoryWarning
    0.40
    Портал
    0.40
    Act Density 0.125%

    No Known Activations