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

    Neuronpedia

    INDEX
    Explanations

    software commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocols
    -0.06
     battled
    -0.06
    (typ
    -0.06
    .ndim
    -0.06
     тим
    -0.06
     бу
    -0.06
    래스
    -0.06
     Apps
    -0.06
     cycling
    -0.06
    اشت
    -0.06
    POSITIVE LOGITS
    current
    0.07
    -mail
    0.07
    <Employee
    0.07
    -current
    0.07
    weather
    0.07
    Current
    0.06
     genç
    0.06
    String
    0.06
    aller
    0.06
    upil
    0.06
    Act Density 0.015%

    No Known Activations