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

    Neuronpedia

    INDEX
    Explanations

    ranking or position

    np_max-act · gemini-2.0-flash

    This neuron fires on Cyrillic-script tokens, i.e. it detects Russian-language text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     giants
    -0.07
     RNA
    -0.07
     enforce
    -0.06
     database
    -0.06
     Monument
    -0.06
    ,rp
    -0.06
     ls
    -0.05
    .table
    -0.05
     bowls
    -0.05
     jurisdiction
    -0.05
    POSITIVE LOGITS
     etme
    0.07
     User
    0.07
     Enabled
    0.07
    ("..
    0.07
     Trần
    0.06
     messing
    0.06
     quyết
    0.06
    (User
    0.06
    ेयर
    0.06
    veyor
    0.06
    Act Density 0.016%

    No Known Activations