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

    Neuronpedia

    INDEX
    Explanations

    customer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ।
    -0.06
    。
    -0.06
    ENGINE
    -0.06
    calculator
    -0.06
     temp
    -0.06
    欧
    -0.06
    设备
    -0.06
    _ENDIAN
    -0.06
    ěli
    -0.06
    Circle
    -0.06
    POSITIVE LOGITS
     outra
    0.06
     CHP
    0.06
     restarted
    0.06
     peasant
    0.06
    ption
    0.06
     scrut
    0.06
     salute
    0.06
     disap
    0.06
    ROWN
    0.06
     　　　　　　　　　　　
    0.06
    Act Density 0.325%

    No Known Activations