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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    联系方式
    -0.07
     lyr
    -0.07
    ตก
    -0.07
     unpaid
    -0.07
    �
    -0.07
     inj
    -0.06
    议题
    -0.06
     çiz
    -0.06
    סך
    -0.06
     Staten
    -0.06
    POSITIVE LOGITS
    Capability
    0.07
    _plain
    0.07
     Mime
    0.07
    Comfort
    0.07
    �
    0.07
    _gps
    0.07
    Tail
    0.07
    -access
    0.07
    引用
    0.07
    али
    0.06
    Act Density 0.003%

    No Known Activations