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

    Neuronpedia

    INDEX
    Explanations

    option

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hearings
    -0.09
     españ
    -0.07
     closures
    -0.06
    utdown
    -0.06
     Coul
    -0.06
     Seminar
    -0.06
    -task
    -0.06
     Rue
    -0.06
    ...)↵
    -0.06
     plains
    -0.06
    POSITIVE LOGITS
    916
    0.06
    ******/↵
    0.06
    ~↵↵
    0.06
     indexer
    0.06
    Multip
    0.06
     conditional
    0.06
    .assertAlmostEqual
    0.06
    .clipsToBounds
    0.06
    040
    0.06
    -ion
    0.06
    Act Density 0.001%

    No Known Activations