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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     he'll
    -0.08
     illeg
    -0.07
     runtime
    -0.07
     bastard
    -0.07
     saint
    -0.07
     rocket
    -0.07
     minner
    -0.07
     disgr
    -0.07
     šk
    -0.07
     भगवान
    -0.07
    POSITIVE LOGITS
     Innovative
    0.11
     Excellence
    0.10
     excellence
    0.09
     innovative
    0.09
     overcoming
    0.09
     Award
    0.09
     Successfully
    0.09
     exemplary
    0.09
     সফল
    0.09
     Awards
    0.08
    Act Density 0.147%

    No Known Activations