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

    Neuronpedia

    INDEX
    Explanations

    lines of code or programming syntax

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

    Code snippets containing "return"

    np_acts-logits-general · gemini-2.0-flash

    formulation and dosage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nullptr
    -0.72
    nullptr
    -0.68
     incentiv
    -0.67
     onboarding
    -0.58
     ImGui
    -0.57
     samot
    -0.57
     foundational
    -0.57
     constexpr
    -0.57
    constexpr
    -0.55
     dédi
    -0.54
    POSITIVE LOGITS
     daß
    0.97
     muß
    0.89
     Daß
    0.78
    faßt
    0.75
     läßt
    0.72
    లాలు
    0.72
     Moslem
    0.70
     mußte
    0.70
     müßte
    0.69
    цездатний
    0.68
    Act Density 0.561%

    No Known Activations