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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .non
    -0.07
     佛
    -0.06
     Discuss
    -0.06
    Чтобы
    -0.06
    copyright
    -0.06
    Neg
    -0.06
    stab
    -0.06
    'image
    -0.06
    '].'/
    -0.05
     tranquil
    -0.05
    POSITIVE LOGITS
    ени
    0.07
    bnb
    0.07
     สพป
    0.07
    ẩn
    0.07
     interpreter
    0.06
     gamers
    0.06
     pornos
    0.06
    >>)
    0.06
    Serve
    0.06
     giai
    0.06
    Act Density 0.001%

    No Known Activations