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

    Neuronpedia

    INDEX
    Explanations

    Mathematical formulas and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucken
    -0.07
     amused
    -0.06
     پرداز
    -0.06
     output
    -0.06
    ترین
    -0.06
     hasNext
    -0.06
    Dispatcher
    -0.06
    Á
    -0.06
    ější
    -0.06
    UMENT
    -0.06
    POSITIVE LOGITS
    Sc
    0.07
     찾
    0.07
    誰
    0.07
     noveller
    0.06
    seniz
    0.06
    issing
    0.06
    IBILITY
    0.06
     impacted
    0.06
    Once
    0.06
    を見る
    0.06
    Act Density 0.118%

    No Known Activations