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

    Neuronpedia

    INDEX
    Explanations

    :=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _orders
    -0.07
    нам
    -0.07
     سیاست
    -0.06
     rời
    -0.06
    alnum
    -0.06
     Transportation
    -0.06
    apr
    -0.06
     giác
    -0.06
    awner
    -0.06
    vanized
    -0.06
    POSITIVE LOGITS
    512
    0.06
     functioning
    0.06
    ี้
    0.06
     플레이
    0.06
    Clone
    0.06
     사항
    0.06
     loc
    0.06
    minating
    0.06
     db
    0.06
     lawful
    0.06
    Act Density 0.001%

    No Known Activations