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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leží
    -0.07
     Assad
    -0.06
     Дж
    -0.06
     dire
    -0.06
    ุตร
    -0.06
     �
    -0.06
    (:
    -0.06
     Streets
    -0.06
    weekday
    -0.06
     주문
    -0.06
    POSITIVE LOGITS
    valuator
    0.07
    .Article
    0.06
     Msg
    0.06
    Gen
    0.06
    erable
    0.06
    Execution
    0.06
    ินการ
    0.06
     نمودار
    0.06
    -drive
    0.06
     intimate
    0.06
    Act Density 0.005%

    No Known Activations