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

    Neuronpedia

    INDEX
    Explanations

    references to celebrities and their lifestyles

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

    royal enthusiasts shed light on prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.48
     فريبيس
    -0.42
    PhysRevLett
    -0.41
     FetchType
    -0.39
    bindingNavigator
    -0.38
    Aholisi
    -0.38
     surla
    -0.38
     CURIAM
    -0.37
    fromnode
    -0.37
    archiviato
    -0.36
    POSITIVE LOGITS
    UnusedPrivate
    0.50
    RegressionTest
    0.50
    Kanpo
    0.47
    Jeografia
    0.46
    TRIBUN
    0.45
    ⋙
    0.43
    μφωνα
    0.43
     ویکی‌پدی
    0.42
     ⁠
    0.41
    didSet
    0.40
    Act Density 0.016%

    No Known Activations