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

    Neuronpedia

    INDEX
    Explanations

    Web protocols/debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     épr
    -0.09
     VALUE
    -0.09
     「
    -0.08
     SCHOOL
    -0.08
    chants
    -0.08
     déroule
    -0.08
    atira
    -0.08
    CHOOL
    -0.08
     CHRIST
    -0.08
    idak
    -0.08
    POSITIVE LOGITS
    接口
    0.12
    واجهة
    0.10
    localhost
    0.10
     localhost
    0.09
     интерф
    0.09
    _interface
    0.09
    通讯
    0.09
    通信
    0.09
    远
    0.09
    .remote
    0.09
    Act Density 0.016%

    No Known Activations