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

    Neuronpedia

    INDEX
    Explanations

    places and squares

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وي
    0.68
    和服务
    0.66
    टर्न
    0.64
    Service
    0.62
    서비스
    0.62
    Dec
    0.62
    Trust
    0.62
    Pend
    0.62
    성과
    0.62
    Response
    0.61
    POSITIVE LOGITS
     Hebrew
    0.78
     morals
    0.77
     aromatherapy
    0.77
     Israël
    0.77
     दुबई
    0.76
    ﮩ
    0.76
     écrire
    0.76
    letscher
    0.75
     pebbles
    0.75
     คณิต
    0.74
    Act Density 0.000%

    No Known Activations