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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    This neuron fires on four-digit numerical tokens representing years or dates in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     RUS
    -0.07
    (Util
    -0.07
    izzes
    -0.07
    \Session
    -0.06
     {*
    -0.06
     Qt
    -0.06
     Federation
    -0.06
    tracks
    -0.06
    (cls
    -0.06
     ÜNİVERSİTESİ
    -0.06
    POSITIVE LOGITS
    ژی
    0.06
     Externí
    0.06
    based
    0.06
     nodeName
    0.06
    EOF
    0.06
    lep
    0.06
    영어
    0.06
    converter
    0.06
     sublic
    0.06
     تحت
    0.06
    Act Density 0.055%

    No Known Activations