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

    Neuronpedia

    INDEX
    Explanations

    product returns and shipping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    locking
    -0.08
    pag
    -0.08
    roker
    -0.07
     enj
    -0.07
    bower
    -0.07
     приходится
    -0.07
     sidste
    -0.07
     flame
    -0.07
     recientemente
    -0.07
     executive
    -0.07
    POSITIVE LOGITS
     Submitted
    0.09
     déchets
    0.09
    污
    0.09
     Shipment
    0.09
     제출
    0.08
    =input
    0.08
     휴
    0.08
    Submitting
    0.08
    返品
    0.08
     recycler
    0.08
    Act Density 0.037%

    No Known Activations