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

    Neuronpedia

    INDEX
    Explanations

    pronouns and auxiliary verbs within a narrative context.

    oai_token-act-pair · gemini-2.0-flash

    Book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.66
     wireType
    -0.60
    enfone
    -0.59
     PROM
    -0.55
     stanie
    -0.55
    Balancer
    -0.54
    shah
    -0.54
    Читати
    -0.54
    ceng
    -0.54
    ToReturn
    -0.54
    POSITIVE LOGITS
    CppMethod
    0.55
    mergeFrom
    0.54
    例文
    0.50
    олові
    0.46
    SPATH
    0.46
     الدولى
    0.45
    astéroïdes
    0.45
    InstrumentedTest
    0.42
    новништво
    0.41
     للمعارف
    0.41
    Act Density 1.436%

    No Known Activations