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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (face
    -0.07
     primaryKey
    -0.07
     entreg
    -0.06
    εβ
    -0.06
    TestCategory
    -0.06
     přitom
    -0.06
    jie
    -0.06
    .Selected
    -0.06
     Publisher
    -0.06
    persist
    -0.06
    POSITIVE LOGITS
    萨
    0.07
     Forbidden
    0.07
    薩
    0.07
    classes
    0.07
    arrays
    0.06
    UCT
    0.06
    shopping
    0.06
     convey
    0.06
     WEIGHT
    0.06
    .movies
    0.06
    Act Density 0.007%

    No Known Activations