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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Każdy
    -0.07
    MessageType
    -0.07
    .Globalization
    -0.06
    .Products
    -0.06
     בגיל
    -0.06
    'er
    -0.06
    的颜色
    -0.06
     Vet
    -0.06
     זוכר
    -0.06
     wooden
    -0.06
    POSITIVE LOGITS
    是什么
    0.07
    poons
    0.07
    ɕ
    0.07
    就行了
    0.07
    埚
    0.06
    ponsored
    0.06
    圹
    0.06
    _payment
    0.06
    bung
    0.06
    LOW
    0.06
    Act Density 0.081%

    No Known Activations