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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash

    This neuron is tuned to detect formal section headings or titles (e.g. “Bypass of Cellular Senescence,” “Occurrence of Power Failure”) in technical or patent‐style texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	Size
    -0.07
    .In
    -0.06
    issions
    -0.06
    .setData
    -0.06
     anus
    -0.06
    (lang
    -0.06
     soaking
    -0.06
     \
    -0.06
     dial
    -0.06
    оді
    -0.06
    POSITIVE LOGITS
     Tune
    0.07
     Representative
    0.06
    bitset
    0.06
    .Ptr
    0.06
     Courtesy
    0.06
    _ARROW
    0.06
     değerli
    0.06
    mando
    0.06
     �
    0.06
     Establishment
    0.06
    Act Density 0.274%

    No Known Activations