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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heads
    -0.30
     LGPL
    -0.30
    头ä¸Ĭ
    -0.27
     Hd
    -0.27
    å±Ĭ
    -0.26
    -license
    -0.26
    jer
    -0.26
    asto
    -0.25
     heads
    -0.25
    _locked
    -0.25
    POSITIVE LOGITS
    çŃ¹èµĦ
    0.31
     Fellow
    0.27
     flight
    0.26
    ç²¾ç¥ŀ
    0.26
    佯
    0.25
    å¹³éĿ¢
    0.25
    Paginator
    0.25
     Sand
    0.25
     Origin
    0.24
    รà¸ĩ
    0.24
    Act Density 0.396%

    No Known Activations