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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .liferay
    -0.07
    ится
    -0.07
     až
    -0.07
     prom
    -0.06
     wild
    -0.06
     arasındaki
    -0.06
    izzato
    -0.06
    -0.06
    onde
    -0.06
    肖
    -0.06
    POSITIVE LOGITS
     waypoints
    0.07
     Vinyl
    0.06
     waypoint
    0.06
     impunity
    0.06
     sunglasses
    0.06
    于是
    0.06
     adher
    0.06
    (option
    0.06
     Preservation
    0.06
    보증금
    0.06
    Act Density 0.009%

    No Known Activations