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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    几乎
    -0.06
     电
    -0.06
    .getActive
    -0.06
     अज
    -0.06
     arom
    -0.06
    ypical
    -0.06
    產品
    -0.06
     форми
    -0.05
    .He
    -0.05
     Datagram
    -0.05
    POSITIVE LOGITS
    Insensitive
    0.07
    healthy
    0.07
    (todo
    0.07
     bers
    0.07
    _vertex
    0.06
     tố
    0.06
    (WIN
    0.06
    則
    0.06
    traits
    0.06
    лі
    0.06
    Act Density 0.001%

    No Known Activations