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

    Neuronpedia

    INDEX
    Explanations

    addition problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    find
    -0.07
     show
    -0.06
     Disability
    -0.06
     eligibility
    -0.06
     shows
    -0.06
     Ag
    -0.06
    ินท
    -0.06
     zprav
    -0.06
    charges
    -0.06
    -0.06
    POSITIVE LOGITS
    AMPL
    0.07
     spline
    0.07
    /wp
    0.07
    [min
    0.07
    Cascade
    0.07
     RTE
    0.06
    ूब
    0.06
     національ
    0.06
    _CAP
    0.06
    _msgs
    0.06
    Act Density 0.023%

    No Known Activations