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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and commands

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

    brackets and right edges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.76
     AssemblyCulture
    -0.71
    RegressionTest
    -0.62
    AISSEE
    -0.61
    ModelAdmin
    -0.60
     مرئيه
    -0.60
     '\\;'
    -0.58
    AccessorTable
    -0.58
    UnsafeEnabled
    -0.56
    abstractmethod
    -0.56
    POSITIVE LOGITS
     aside
    0.36
     граждан
    0.34
     direct
    0.34
     gray
    0.34
     traveling
    0.34
     forward
    0.33
     action
    0.33
     ground
    0.33
     internal
    0.32
     theater
    0.32
    Act Density 0.043%

    No Known Activations