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

    Neuronpedia

    INDEX
    Explanations

    job postings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dims
    -0.07
     Disposable
    -0.07
    ौ
    -0.07
     án
    -0.06
    (factory
    -0.06
     pervasive
    -0.06
     departure
    -0.06
     الذين
    -0.06
    (ag
    -0.06
    وبی
    -0.06
    POSITIVE LOGITS
    ],[-
    0.06
     shelves
    0.06
    สว
    0.06
     Snow
    0.06
    ibile
    0.06
    plt
    0.06
     EW
    0.06
     Choose
    0.06
     spaced
    0.06
    运动
    0.06
    Act Density 0.010%

    No Known Activations