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

    Neuronpedia

    INDEX
    Explanations

    defect

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of anatomical defects (especially surgical or pathological “defects”) often qualified by size or context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    velop
    -0.07
     اه
    -0.07
    	async
    -0.07
    .tag
    -0.07
     async
    -0.07
    劉
    -0.06
     spells
    -0.06
    узы
    -0.06
     Slayer
    -0.06
     hobby
    -0.06
    POSITIVE LOGITS
    фф
    0.07
     deficit
    0.07
    .default
    0.06
    _DEVICES
    0.06
     العق
    0.06
     foreigners
    0.06
    Gap
    0.06
    ोज
    0.06
     nek
    0.06
     لكرة
    0.06
    Act Density 0.005%

    No Known Activations