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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    This neuron activates on repeated occurrences of the phrase “the same.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    scribers
    -0.07
    ढ
    -0.07
    orro
    -0.07
     RuntimeMethod
    -0.06
    .repository
    -0.06
     Cotton
    -0.06
     DropDownList
    -0.06
    vanized
    -0.06
     详情
    -0.06
    enan
    -0.06
    POSITIVE LOGITS
     embarrassed
    0.07
    �
    0.07
     acompañ
    0.06
    	cancel
    0.06
    �
    0.06
     되
    0.06
     ав
    0.06
     same
    0.06
     socialist
    0.06
     WN
    0.06
    Act Density 0.020%

    No Known Activations