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

    Neuronpedia

    INDEX
    Explanations

    protobuf and telegram bots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ^{[\
    0.44
    ToUpper
    0.44
    InterfaceLine
    0.42
    ConformanceMode
    0.41
    ReadAll
    0.41
    ^{[
    0.41
    PostConstruct
    0.41
     रोकने
    0.39
     الآ
    0.38
     setLayout
    0.38
    POSITIVE LOGITS
    pb
    0.49
    姬
    0.43
    "
    0.43
    smithy
    0.42
    mysql
    0.40
    “
    0.40
    contain
    0.40
    app
    0.39
    atypes
    0.39
    gax
    0.39
    Act Density 0.006%

    No Known Activations