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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols typically used in programming or mathematical notations

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

    closing braces or brackets used in mathematical expressions or code

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

    code blocks with surrounding braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.65
     '\\;'
    -0.62
    anskje
    -0.54
    ItemGroup
    -0.50
    ûr
    -0.49
    جغرافيا
    -0.49
    oredCriteria
    -0.48
    ThroughAttribute
    -0.48
    estor
    -0.48
     مواليد
    -0.48
    POSITIVE LOGITS
    InSection
    0.67
     handker
    0.60
    ANDUM
    0.54
    IBase
    0.52
     CommonModule
    0.52
     handkerchief
    0.51
     tassels
    0.50
     Anato
    0.50
     Wiktionnaire
    0.50
    }\}
    0.49
    Act Density 0.005%

    No Known Activations