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

    Neuronpedia

    INDEX
    Explanations

    é

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spill
    -0.08
    spill
    -0.08
     Aging
    -0.08
     MV
    -0.08
    spread
    -0.08
     lowering
    -0.07
    ainment
    -0.07
     Adjustment
    -0.07
     adjusted
    -0.07
     adjustments
    -0.07
    POSITIVE LOGITS
     comprises
    0.10
     webpack
    0.09
     suffisamment
    0.08
    Enough
    0.08
    enha
    0.08
     sufficiently
    0.08
     convain
    0.08
     تعالى
    0.08
     sinon
    0.08
     Enough
    0.08
    Act Density 0.001%

    No Known Activations