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

    Neuronpedia

    INDEX
    Explanations

    symbols and expressions related to mathematical definitions and relationships in equations

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

    LaTeX code snippets

    np_acts-logits-general · gemini-2.0-flash

    math and programming notation separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.48
     SafeMath
    -0.44
    SPATH
    -0.43
     rospy
    -0.43
    XCTAssert
    -0.42
     bet
    -0.41
    assertj
    -0.40
    bet
    -0.38
    ifflin
    -0.38
     Say
    -0.38
    POSITIVE LOGITS
    enumi
    0.84
     CreateTagHelper
    0.80
    Predecesor
    0.79
    AddTagHelper
    0.76
     للمعارف
    0.75
    __'
    0.71
    enumii
    0.71
     AssemblyCompany
    0.71
    TagMode
    0.70
     فريبيس
    0.70
    Act Density 0.055%

    No Known Activations