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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besie
    -0.07
    .Byte
    -0.07
    ﺆ
    -0.07
     consultant
    -0.07
    暫
    -0.07
    .Tx
    -0.07
    okino
    -0.07
     теат
    -0.07
     Meet
    -0.06
     kardeş
    -0.06
    POSITIVE LOGITS
    userData
    0.07
    nst
    0.07
    avy
    0.07
    ingredients
    0.06
     wildcard
    0.06
    units
    0.06
    腿部
    0.06
    ordinates
    0.06
    价格
    0.06
     dolphin
    0.06
    Act Density 0.006%

    No Known Activations