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

    Neuronpedia

    INDEX
    Explanations

    Code license agreements file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sent
    -0.07
     gây
    -0.07
     employ
    -0.07
     hitters
    -0.06
     information
    -0.06
    Nx
    -0.06
     media
    -0.06
     tìm
    -0.06
    :^(
    -0.06
    _Matrix
    -0.06
    POSITIVE LOGITS
    boost
    0.07
     totiž
    0.07
    شن
    0.06
    PLUS
    0.06
    نام
    0.06
    .course
    0.06
     boiler
    0.06
     بانک
    0.06
    �
    0.06
    ़ो
    0.05
    Act Density 0.001%

    No Known Activations