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

    Neuronpedia

    INDEX
    Explanations

    career backgrounds and job roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Conference
    0.70
    Academy
    0.70
    Award
    0.68
    パートナー
    0.68
    艺术家
    0.68
    Awards
    0.67
     талант
    0.66
     ويع
    0.64
    Collaboration
    0.64
    Origin
    0.64
    POSITIVE LOGITS
     bancos
    0.92
     durations
    0.77
     greasy
    0.75
     tampon
    0.74
     vantage
    0.73
     antes
    0.73
     banks
    0.73
     emulsions
    0.71
     holes
    0.71
     insides
    0.70
    Act Density 0.107%

    No Known Activations