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

    Neuronpedia

    INDEX
    Explanations

    lists of names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ANAL
    -0.07
     Password
    -0.07
     biggest
    -0.07
    орони
    -0.07
    _PROPERTY
    -0.06
    xBE
    -0.06
    atica
    -0.06
     prayer
    -0.06
    visitor
    -0.06
    одейств
    -0.06
    POSITIVE LOGITS
    죽
    0.06
     بزر
    0.06
    ázev
    0.06
     usually
    0.06
     Sundays
    0.06
    creating
    0.06
     farmers
    0.06
    िनक
    0.06
     ADD
    0.06
     일정
    0.06
    Act Density 0.023%

    No Known Activations