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
     Bronze
    -0.07
    (Spring
    -0.07
    _UTF
    -0.07
     nhiệt
    -0.06
    _Part
    -0.06
    Reject
    -0.06
    (rank
    -0.06
     pseudo
    -0.06
    /fonts
    -0.06
     вывод
    -0.06
    POSITIVE LOGITS
     biết
    0.07
    ?“↵↵
    0.06
    详情
    0.06
     _______,
    0.06
     Cobb
    0.06
    ？”
    0.06
     Gä
    0.06
    !”
    0.06
    ۀ
    0.06
     psyched
    0.06
    Act Density 0.015%

    No Known Activations