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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aired
    -0.09
     collectiv
    -0.08
     wê
    -0.08
     Transmission
    -0.08
    mén
    -0.08
     �
    -0.08
    )add
    -0.08
     rue
    -0.08
     Packed
    -0.08
    INET
    -0.08
    POSITIVE LOGITS
     trained
    0.09
     assisting
    0.08
    生成
    0.08
    助手
    0.08
     capability
    0.08
     assist
    0.08
     capabilities
    0.08
     કરી
    0.08
     способен
    0.08
     helping
    0.07
    Act Density 0.079%

    No Known Activations