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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    索
    -0.07
    ollipop
    -0.06
    NUM
    -0.06
    _svg
    -0.06
    omed
    -0.06
    assert
    -0.06
    σκ
    -0.06
    123
    -0.06
     warehouses
    -0.06
    won
    -0.06
    POSITIVE LOGITS
     прием
    0.07
    Creators
    0.07
    unner
    0.07
     中国
    0.06
     ],
    0.06
     (_.
    0.06
     CONTRACT
    0.06
    (newUser
    0.06
     delve
    0.06
    '},
↵
    0.06
    Act Density 0.284%

    No Known Activations