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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rinse
    -0.08
    ?,
    -0.07
    WT
    -0.06
     -------------
    -0.06
     GLFW
    -0.06
    .putInt
    -0.06
     confines
    -0.06
     UPS
    -0.06
    Nom
    -0.06
    uento
    -0.06
    POSITIVE LOGITS
     Дж
    0.07
     deutschen
    0.06
    _device
    0.06
     Số
    0.06
     아무
    0.06
     ㅡ
    0.06
     kims
    0.06
     Develop
    0.06
     Des
    0.06
    hua
    0.06
    Act Density 0.014%

    No Known Activations