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

    Neuronpedia

    INDEX
    Explanations

    elements or features in programming or computational contexts

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

    Numbers, often with punctuation or units

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yaşam
    -0.41
    dibles
    -0.41
    style
    -0.41
    ัญ
    -0.40
    estes
    -0.40
     nhất
    -0.40
     Estad
    -0.39
     метра
    -0.39
    olis
    -0.38
    兄
    -0.38
    POSITIVE LOGITS
    RegistryLite
    0.96
    الدراسه
    0.90
     beginnetje
    0.78
     JpaRepository
    0.76
    ReusableCell
    0.75
    انجليز
    0.72
     pinulongan
    0.71
     متعلقه
    0.69
    Билгалдахарш
    0.69
    RectangleBorder
    0.68
    Act Density 0.434%

    No Known Activations