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

    Neuronpedia

    INDEX
    Explanations

    ide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Congratulations
    -0.06
     отвеч
    -0.06
     был
    -0.06
     наяв
    -0.06
     Baz
    -0.06
     resignation
    -0.06
     Dice
    -0.06
    //-----------------------------------------------------------------------------↵
    -0.06
     Abrams
    -0.06
     React
    -0.05
    POSITIVE LOGITS
    eline
    0.07
     mt
    0.06
    9
    0.06
    %);↵
    0.06
     الذ
    0.06
    ker
    0.06
    !==
    0.06
     inner
    0.06
    -group
    0.06
    1
    0.06
    Act Density 0.000%

    No Known Activations