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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens, so it isn’t detecting any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     خدم
    -0.07
     striped
    -0.06
    	LP
    -0.06
    -policy
    -0.06
     Nez
    -0.06
    _teams
    -0.06
    rates
    -0.06
    tor
    -0.06
     sight
    -0.06
    turned
    -0.06
    POSITIVE LOGITS
    اورزی
    0.08
    ै?
    0.07
     иде
    0.06
     brain
    0.06
     UserRepository
    0.06
     francais
    0.06
     civilizations
    0.06
    []={
    0.06
    制度
    0.06
    震
    0.06
    Act Density 0.009%

    No Known Activations