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

    Neuronpedia

    INDEX
    Explanations

    references to extended or enhanced features and classifications, particularly in technical and medical contexts

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

    extended modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ins
    -0.39
     getIndex
    -0.36
    atchewan
    -0.34
    Зноскі
    -0.33
     ün
    -0.33
    furter
    -0.32
    IRING
    -0.32
    🥞
    -0.32
     rub
    -0.31
     nazis
    -0.31
    POSITIVE LOGITS
    extended
    0.74
    Extended
    0.73
     Extended
    0.72
     extended
    0.69
    Personendaten
    0.57
     erweiterten
    0.57
     élar
    0.56
    RegressionTest
    0.55
     Enhanced
    0.55
     expanded
    0.55
    Act Density 0.313%

    No Known Activations