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

    Neuronpedia

    INDEX
    Explanations

    module

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (android
    -0.07
    法人
    -0.07
    出发
    -0.07
     있도록
    -0.06
    -top
    -0.06
    .Material
    -0.06
    万元
    -0.06
     числ
    -0.06
     numerator
    -0.06
    .SerializedName
    -0.06
    POSITIVE LOGITS
    _CLI
    0.07
    omid
    0.07
    홈
    0.07
     chores
    0.07
     dạy
    0.07
    panies
    0.07
     Tir
    0.07
     ogóle
    0.07
    _CLOSED
    0.06
    OrElse
    0.06
    Act Density 0.001%

    No Known Activations