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

    Neuronpedia

    INDEX
    Explanations

    key phrases and results related to scientific research and findings

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

    finding or reporting results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Liens
    -0.48
    saya
    -0.47
     للاسماء
    -0.47
     Hermans
    -0.42
    zimmer
    -0.42
    kolor
    -0.42
    FieldDescriptor
    -0.42
    ódó
    -0.41
    ########.
    -0.41
    𐤔
    -0.41
    POSITIVE LOGITS
    RegressionTest
    0.51
     NSCoder
    0.45
     ویکی‌پدیا
    0.45
     defaultstate
    0.44
    principalTable
    0.41
     שוליים
    0.39
    CloseOperation
    0.37
    SuppressLint
    0.37
     veckor
    0.35
    ActionCreators
    0.35
    Act Density 0.852%

    No Known Activations