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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude with punctuation, as well as first person pronouns, contractions, and words expressing opinions

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.67
    tagHelperRunner
    -0.65
     Audiodateien
    -0.61
    NonQuery
    -0.58
    Diweddarwch
    -0.56
     ostavi
    -0.56
     שוליים
    -0.56
    fide
    -0.55
    findpost
    -0.54
    GEBURTSDATUM
    -0.54
    POSITIVE LOGITS
    styleable
    0.47
     élevées
    0.47
     estuviera
    0.46
     svårt
    0.45
    AddHtmlAttribute
    0.44
     Efq
    0.44
    msgTypes
    0.44
     Alha
    0.44
     laiko
    0.43
     насељу
    0.43
    Act Density 2.107%

    No Known Activations