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

    Neuronpedia

    INDEX
    Explanations

    done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etypes
    -0.06
    (case
    -0.06
     quart
    -0.06
     safety
    -0.06
     SENSOR
    -0.06
     myriad
    -0.06
    _CLASS
    -0.06
    [col
    -0.06
    ?!
    -0.06
     mới
    -0.06
    POSITIVE LOGITS
     done
    0.15
     Done
    0.08
     DONE
    0.08
     Official
    0.08
    {})
    0.07
    Doug
    0.07
    руется
    0.06
    Done
    0.06
    unal
    0.06
     allotted
    0.06
    Act Density 0.010%

    No Known Activations