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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

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

    same word across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.65
    دانشنامهٔ
    -0.60
     يتيمه
    -0.58
    utilisons
    -0.57
     المعيارى
    -0.54
    Наводи
    -0.54
    -0.53
    -------------</
    -0.51
    RUnlock
    -0.51
    المشاركات
    -0.50
    POSITIVE LOGITS
     same
    0.46
     mêmes
    0.41
     equally
    0.41
     misma
    0.38
     aynı
    0.37
     mismo
    0.36
     mismas
    0.36
     ganas
    0.36
    Same
    0.35
     mesma
    0.34
    Act Density 0.076%

    No Known Activations