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

    Neuronpedia

    INDEX
    Explanations

    better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Merr
    -0.06
    -0.06
     navigate
    -0.06
    Part
    -0.06
    .JWT
    -0.06
    Delete
    -0.06
    ераль
    -0.06
     مراج
    -0.06
     trek
    -0.06
     갈
    -0.06
    POSITIVE LOGITS
    ♪
    0.07
    inactive
    0.06
    _;↵↵
    0.06
    .stdout
    0.06
    "];↵↵
    0.06
    吗
    0.06
    ]);↵
    0.06
    lady
    0.06
    udos
    0.06
     '''
↵
    0.06
    Act Density 0.011%

    No Known Activations