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

    Neuronpedia

    INDEX
    Explanations

    Robotics competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infrastructure
    -0.07
     hedge
    -0.07
     Nose
    -0.06
     simplified
    -0.06
    /ws
    -0.06
    thew
    -0.06
    .priority
    -0.06
     Yah
    -0.06
     hire
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Werner
    0.06
    нення
    0.06
    :utf
    0.06
     activ
    0.06
     tato
    0.06
    +v
    0.06
     střední
    0.06
     آلة
    0.06
    　　 　 　 　
    0.06
    　　　　　 　
    0.06
    Act Density 0.015%

    No Known Activations