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

    Neuronpedia

    INDEX
    Explanations

    reputation management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _news
    -0.08
     tripod
    -0.07
     sách
    -0.06
     DHCP
    -0.06
     lịch
    -0.06
     DEN
    -0.06
     الخاصة
    -0.06
    �
    -0.06
     Mesh
    -0.06
     LEN
    -0.06
    POSITIVE LOGITS
    anted
    0.06
    ANTED
    0.06
    اط
    0.06
    VED
    0.06
    -s
    0.06
    -full
    0.06
    -m
    0.06
    ्ट
    0.06
     sure
    0.06
    ={{↵
    0.06
    Act Density 0.006%

    No Known Activations