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

    Neuronpedia

    INDEX
    Explanations

    lost recordings/broadcasts

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (years, dates, episode numbers, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rent
    -0.07
     زمان
    -0.07
     immediate
    -0.06
    ۱۰
    -0.06
    Tween
    -0.06
    /ns
    -0.06
    вався
    -0.06
     Value
    -0.06
    async
    -0.06
     Crossing
    -0.06
    POSITIVE LOGITS
    obre
    0.06
    /rem
    0.06
     OPER
    0.06
    phyl
    0.06
     };↵↵↵
    0.06
    ovala
    0.06
    .Tele
    0.06
    (groupId
    0.06
     кін
    0.06
     fixture
    0.06
    Act Density 0.014%

    No Known Activations