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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    笸
    -0.08
     comparing
    -0.07
     לוק
    -0.07
    ่ง
    -0.07
     Microwave
    -0.07
    콥
    -0.07
    光荣
    -0.07
    سار
    -0.07
    客车
    -0.07
    lew
    -0.07
    POSITIVE LOGITS
    Regional
    0.07
    Usuarios
    0.07
    ları
    0.07
    interpreter
    0.07
    border
    0.07
     Fact
    0.07
    基础设施
    0.06
    Payments
    0.06
    㴔
    0.06
    BOOST
    0.06
    Act Density 0.004%

    No Known Activations