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

    Neuronpedia

    INDEX
    Explanations

    code-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    携手
    -0.07
     طريق
    -0.07
     incentiv
    -0.06
    这几天
    -0.06
     Ahead
    -0.06
    fortunately
    -0.06
     TRACK
    -0.06
     excursion
    -0.06
    ROLL
    -0.06
    checkpoint
    -0.06
    POSITIVE LOGITS
    rdf
    0.08
     różnych
    0.07
    سة
    0.07
    ası
    0.07
    梦见
    0.07
    ，
    0.07
    هما
    0.07
    �
    0.07
    üstü
    0.07
    ку
    0.06
    Act Density 0.151%

    No Known Activations