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

    Neuronpedia

    INDEX
    Explanations

    augment or mentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    思考
    -0.07
    _ctrl
    -0.07
     kriz
    -0.07
     klas
    -0.07
     dici
    -0.07
     clazz
    -0.06
     records
    -0.06
     LAB
    -0.06
    _fil
    -0.06
     spin
    -0.06
    POSITIVE LOGITS
     augment
    0.13
     augmented
    0.11
     aument
    0.09
    Aug
    0.09
     augmentation
    0.09
     Aug
    0.08
    _aug
    0.08
     aug
    0.07
     Rou
    0.07
    ụ
    0.07
    Act Density 0.007%

    No Known Activations