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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ueling
    -0.06
    ickt
    -0.06
    ические
    -0.06
     ridiculously
    -0.06
    inkle
    -0.06
     juris
    -0.06
     bondage
    -0.06
     generous
    -0.06
    真
    -0.06
     rude
    -0.06
    POSITIVE LOGITS
    485
    0.06
    discover
    0.06
    camera
    0.06
    <center
    0.06
     Variables
    0.06
    anlar
    0.06
    atonin
    0.06
    Coordinate
    0.06
    akening
    0.06
    =top
    0.06
    Act Density 0.000%

    No Known Activations