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

    Neuronpedia

    INDEX
    Explanations

    attributes related to reliability and consistency in performance or processes

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

    describing appropriate qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.42
    ckså
    -0.38
     kasarigan
    -0.37
     Alte
    -0.36
    CloseOperation
    -0.36
    ┑
    -0.35
    MessageTagHelper
    -0.35
    WarningLevel
    -0.35
    xac
    -0.35
     Wikimedijinoj
    -0.35
    POSITIVE LOGITS
     dieß
    0.50
     intptr
    0.48
    CppMethod
    0.48
     spesa
    0.47
     ſein
    0.45
    findpost
    0.44
     Geſ
    0.43
    grimas
    0.42
     Ejecutivo
    0.42
     émotion
    0.42
    Act Density 0.208%

    No Known Activations