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

    Neuronpedia

    INDEX
    Explanations

    signing documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .birth
    -0.07
    .Usuario
    -0.06
     spraying
    -0.06
    컵
    -0.06
     Drinking
    -0.06
     Loader
    -0.06
     sond
    -0.06
     верх
    -0.06
    >,
    -0.06
     счет
    -0.06
    POSITIVE LOGITS
    holiday
    0.07
    ี.
    0.07
     آمده
    0.07
    ALIGN
    0.06
    ิช
    0.06
     PyTuple
    0.06
    oulouse
    0.06
    ,proto
    0.06
    ��
    0.06
    ordinates
    0.06
    Act Density 0.019%

    No Known Activations