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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     centers
    -0.08
     Assist
    -0.07
     suitcase
    -0.07
    urchase
    -0.07
    레스
    -0.07
    /upload
    -0.06
     Phú
    -0.06
    RESSED
    -0.06
    grp
    -0.06
     Campus
    -0.06
    POSITIVE LOGITS
     Before
    0.12
    Before
    0.12
     before
    0.08
    before
    0.06
    ,NULL
    0.06
     Saunders
    0.06
     Prior
    0.06
    .open
    0.06
    '||
    0.06
     mohla
    0.06
    Act Density 0.011%

    No Known Activations