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

    Neuronpedia

    INDEX
    Explanations

    structural elements and numerical references in a variety of contexts

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

    numbers and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sünde
    -0.44
     fréquent
    -0.41
     varones
    -0.41
    kehren
    -0.41
     locaux
    -0.40
     étrangères
    -0.39
     betek
    -0.38
     cielos
    -0.38
     Gedanke
    -0.38
     quedarse
    -0.37
    POSITIVE LOGITS
     فريبيس
    0.75
    تقاوى
    0.61
     Италијани
    0.60
     nahilalakip
    0.57
    Aholisi
    0.56
    GOTREF
    0.55
    PMailer
    0.54
     يتيمه
    0.51
    drawSprites
    0.50
    kloped
    0.49
    Act Density 0.139%

    No Known Activations