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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash

    This neuron never activates (i.e. it appears to be “dead” and does not detect any pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gere
    -0.07
     Manor
    -0.07
     суп
    -0.07
     plá
    -0.07
     refrain
    -0.06
     ＜
    -0.06
    akra
    -0.06
     kar
    -0.06
     itemprop
    -0.06
     тов
    -0.06
    POSITIVE LOGITS
     resignation
    0.07
    śli
    0.07
     checking
    0.07
     Working
    0.07
    	as
    0.07
    Then
    0.06
     rocking
    0.06
    _SID
    0.06
     Qualified
    0.06
     Ludwig
    0.06
    Act Density 0.003%

    No Known Activations