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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     будів
    -0.06
    Gam
    -0.06
    Bob
    -0.06
    .imp
    -0.06
    ius
    -0.06
     Legendary
    -0.06
     Won
    -0.06
    जब
    -0.06
    ITERAL
    -0.06
    ใ
    -0.06
    POSITIVE LOGITS
     말
    0.07
    xl
    0.07
     Lund
    0.06
    kd
    0.06
    -less
    0.06
    οκ
    0.06
    unders
    0.06
    于
    0.06
     distinction
    0.06
     lbs
    0.06
    Act Density 0.004%

    No Known Activations