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

    Neuronpedia

    INDEX
    Explanations

    validation checks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adapt
    -0.07
     通
    -0.06
     وذلك
    -0.06
    .ShouldBe
    -0.06
     drawn
    -0.06
    Ό
    -0.06
     cand
    -0.06
    enumerate
    -0.06
     theres
    -0.06
     Pole
    -0.06
    POSITIVE LOGITS
     FLAGS
    0.08
    거래
    0.07
    냥
    0.07
     shields
    0.07
    /order
    0.06
     Pets
    0.06
    ................................
    0.06
    δα
    0.06
    (util
    0.06
     lingu
    0.06
    Act Density 0.005%

    No Known Activations