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

    Neuronpedia

    INDEX
    Explanations

    Р

    np_max-act · gemini-2.0-flash

    The neuron never activates—it does not respond to any tokens (“dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     BYTE
    -0.07
    663
    -0.07
     functionName
    -0.07
     вну
    -0.06
     blk
    -0.06
     neglect
    -0.06
     culprit
    -0.06
    	layer
    -0.06
     Wander
    -0.06
    Curso
    -0.06
    POSITIVE LOGITS
    兴
    0.07
     deactivate
    0.07
     ===>
    0.07
    ‌ن
    0.06
    财
    0.06
     參
    0.06
     Lod
    0.06
    idel
    0.06
     xác
    0.06
    =",
    0.06
    Act Density 0.015%

    No Known Activations