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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash

    terms related to software licensing and legal disclaimers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron consistently activates on the word “limitations” (as found in Apache-style license boilerplate).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gio
    -0.06
     BOOK
    -0.06
     Intro
    -0.06
     narrower
    -0.06
     bốn
    -0.06
     Ready
    -0.06
     Marble
    -0.06
     Betting
    -0.06
     Bry
    -0.06
     Cable
    -0.06
    POSITIVE LOGITS
    limitations
    0.07
    pad
    0.07
    Apr
    0.06
    SDK
    0.06
    /w
    0.06
    ностей
    0.06
    (@"%@",
    0.06
    ,min
    0.06
    "\
    0.06
    (rc
    0.06
    Act Density 0.000%

    No Known Activations