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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     WebSocket
    -0.07
    Atlanta
    -0.06
    /Area
    -0.06
     TMZ
    -0.06
    .Ribbon
    -0.06
    아파트
    -0.06
     XSS
    -0.06
     '\\'
    -0.06
    elib
    -0.06
    โรง
    -0.06
    POSITIVE LOGITS
    (cube
    0.07
    :\/\/
    0.07
     annoyance
    0.07
    autorelease
    0.06
    :pointer
    0.06
     přesně
    0.06
    REQUEST
    0.06
     vůči
    0.06
     Du
    0.06
     Things
    0.06
    Act Density 0.041%

    No Known Activations