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

    Neuronpedia

    INDEX
    Explanations

    statistical metrics and quantifiable data related to numbers and percentages

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

    rates and proportions of change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.56
    IUrlHelper
    -0.50
     تضيفلها
    -0.46
    Diwedd
    -0.46
    TestingModule
    -0.44
     AssemblyTitle
    -0.44
    Indented
    -0.43
    AutoModerator
    -0.43
    SequentialGroup
    -0.42
     contextLoads
    -0.42
    POSITIVE LOGITS
     chiffre
    0.46
     considerably
    0.45
     cifra
    0.43
     dép
    0.43
    Література
    0.43
     steadily
    0.43
     paltry
    0.41
    delwed
    0.40
    Chang
    0.39
    üyor
    0.39
    Act Density 0.031%

    No Known Activations