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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and conjunctions

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

    universal indicating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Twitter
    -0.39
     Twitch
    -0.38
    define
    -0.37
     fren
    -0.35
     Twitter
    -0.35
     Resident
    -0.35
    spyOn
    -0.35
    Twitch
    -0.35
    Resident
    -0.35
    Employee
    -0.34
    POSITIVE LOGITS
     universelle
    0.63
    IntoConstraints
    0.63
     universale
    0.60
     resourceCulture
    0.57
    Personensuche
    0.56
     universel
    0.54
     disambiguazione
    0.54
     universality
    0.52
     universal
    0.52
     CreateTagHelper
    0.52
    Act Density 0.061%

    No Known Activations