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
     award
    -0.90
     Award
    -0.87
     Awards
    -0.85
     awards
    -0.82
    Awards
    -0.78
    Award
    -0.76
     AWARD
    -0.73
     AWARDS
    -0.71
     prêmio
    -0.68
    award
    -0.66
    POSITIVE LOGITS
    migrationBuilder
    0.70
    évaluateur
    0.69
     NSCoder
    0.69
    KURZBESCHREIBUNG
    0.62
     препратки
    0.61
     endforeach
    0.61
    __":
    0.61
    ołnier
    0.60
    сылкі
    0.59
    orsese
    0.59
    Act Density 0.019%

    No Known Activations