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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ually
    -0.06
     �
    -0.06
    	real
    -0.06
    (withId
    -0.06
    -forward
    -0.06
    妙
    -0.06
    cence
    -0.06
    Transfer
    -0.06
    .DATA
    -0.06
    olver
    -0.06
    POSITIVE LOGITS
     shields
    0.07
    异常
    0.06
    лон
    0.06
    /tasks
    0.06
     lacked
    0.06
    (InputStream
    0.06
    'était
    0.06
     pills
    0.06
     Afghan
    0.06
     شمالی
    0.06
    Act Density 0.018%

    No Known Activations