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

    Neuronpedia

    INDEX
    Explanations

    microsoft

    np_max-act · gemini-2.0-flash

    This neuron is looking for XML namespace declarations (e.g., xmlns="…" or xmlns:prefix="…") in markup.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     assault
    -0.07
    Psi
    -0.07
    στη
    -0.07
    ppe
    -0.07
    (cls
    -0.06
     plagued
    -0.06
    _STENCIL
    -0.06
     ethanol
    -0.06
     sender
    -0.06
    _update
    -0.06
    POSITIVE LOGITS
     consequently
    0.07
     существ
    0.07
    卻
    0.06
    Cantidad
    0.06
    Jets
    0.06
    fluence
    0.06
     steep
    0.06
     influencers
    0.06
     Duis
    0.06
     花
    0.06
    Act Density 0.006%

    No Known Activations