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

    Neuronpedia

    INDEX
    Explanations

    tariffs and subscriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ônico
    0.70
     интерпре
    0.70
     ശക്ത
    0.69
     अस्प
    0.68
     sklearn
    0.67
     là
    0.66
    fund
    0.66
     istot
    0.66
     ঐক্য
    0.66
     extrêmement
    0.65
    POSITIVE LOGITS
     tariffs
    1.04
     Tariff
    0.97
     tariff
    0.97
     agendas
    0.94
     subscriptions
    0.92
     agenda
    0.90
     horaires
    0.88
     inscriptions
    0.86
     newsletters
    0.85
     tarif
    0.85
    Act Density 0.154%

    No Known Activations