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

    Neuronpedia

    INDEX
    Explanations

    Common English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     br
    -0.07
    slu
    -0.07
    남
    -0.06
    .vertices
    -0.06
     Hüs
    -0.06
     나가
    -0.06
     vestib
    -0.06
     �
    -0.06
     handsome
    -0.06
     tục
    -0.06
    POSITIVE LOGITS
     Prague
    0.07
    owing
    0.06
    […
    0.06
     개발
    0.06
    Jose
    0.06
    /kernel
    0.06
    ipher
    0.06
     posible
    0.06
    AUTH
    0.06
    OAD
    0.06
    Act Density 0.135%

    No Known Activations