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

    Neuronpedia

    INDEX
    Explanations

    separators or dividers in structured text, particularly those denoted by "===" or similar formatting markers

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

    ===================

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TableColumn
    -0.49
    #
    -0.48
    MemoryWarning
    -0.48
     monaco
    -0.48
    istoitu
    -0.47
    barrow
    -0.45
    IContainer
    -0.44
    SizeMode
    -0.43
     Nong
    -0.43
     checkBox
    -0.43
    POSITIVE LOGITS
    ===
    2.08
    ====
    1.22
    ==="
    1.09
    =======
    1.07
    =====
    0.98
    ==='
    0.90
    ======
    0.87
    ===============
    0.83
    !==
    0.82
     ====
    0.75
    Act Density 0.046%

    No Known Activations