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

    Neuronpedia

    INDEX
    Explanations

    objective

    np_max-act · gemini-2.0-flash

    This neuron never activates on any of the document tokens—it appears to be effectively “dead.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SCRIPT
    -0.07
     orient
    -0.07
    τολ
    -0.07
     toll
    -0.07
    anas
    -0.06
     wrest
    -0.06
     low
    -0.06
     Yep
    -0.06
    ंट
    -0.06
     Levels
    -0.06
    POSITIVE LOGITS
    VO
    0.07
     oid
    0.07
     kako
    0.06
     uu
    0.06
    ivo
    0.06
     mük
    0.06
    .bg
    0.06
    .GroupBox
    0.06
    =z
    0.06
     prostor
    0.06
    Act Density 0.012%

    No Known Activations