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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names and places

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

    Non-English language or mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    specific prefixes followed by specific characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lar
    -0.72
    ın
    -0.68
    ların
    -0.67
    ları
    -0.65
    nak
    -0.63
    dır
    -0.58
    lık
    -0.57
    lla
    -0.56
     mı
    -0.52
    lari
    -0.51
    POSITIVE LOGITS
     فريبيس
    0.68
    رشف
    0.63
     المعيارى
    0.62
     recherchez
    0.60
    eleste
    0.60
     disambiguazione
    0.59
    GEBURTSDATUM
    0.58
    ılıyor
    0.58
     Signalez
    0.58
     FetchType
    0.58
    Act Density 0.073%

    No Known Activations