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

    Neuronpedia

    INDEX
    Explanations

    Physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ็บ
    -0.07
     นาง
    -0.06
    ưu
    -0.06
    ooled
    -0.06
    ()<
    -0.06
    átu
    -0.06
    ульт
    -0.06
    exo
    -0.06
     الموقع
    -0.06
     recognized
    -0.06
    POSITIVE LOGITS
    pollo
    0.06
    Π
    0.06
    ام
    0.06
     männ
    0.06
     WOM
    0.06
     اختلاف
    0.06
    .start
    0.06
     iterator
    0.06
     женщин
    0.06
     İs
    0.06
    Act Density 0.000%

    No Known Activations