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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARR
    -0.07
    陵
    -0.07
    datasets
    -0.06
    (code
    -0.06
     SKU
    -0.06
    MUX
    -0.06
    ugeot
    -0.06
    stocks
    -0.06
    top
    -0.06
     MV
    -0.06
    POSITIVE LOGITS
     đánh
    0.06
     Franti
    0.06
     použí
    0.06
    pll
    0.06
    ]=$
    0.06
    _purchase
    0.06
    Bone
    0.06
     ['$
    0.06
     contraceptive
    0.06
     ningún
    0.06
    Act Density 0.059%

    No Known Activations