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

    Neuronpedia

    INDEX
    Explanations

    binary code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unset
    -0.07
     Conrad
    -0.07
    즌
    -0.06
    (er
    -0.06
    sticks
    -0.06
    imeter
    -0.06
     btw
    -0.06
     OG
    -0.06
     postseason
    -0.06
     budget
    -0.06
    POSITIVE LOGITS
    Gets
    0.07
    Mexico
    0.06
    _CANNOT
    0.06
    \"",
    0.06
     onNext
    0.06
    %',↵
    0.06
     香港
    0.06
    Xã
    0.06
    收
    0.06
    0.06
    Act Density 0.000%

    No Known Activations