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

    Neuronpedia

    INDEX
    Explanations

    electrical outlets and switches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esperienza
    0.84
    arrivée
    0.84
     Интер
    0.82
     Royaume
    0.81
    novu
    0.81
     Chromium
    0.80
     якому
    0.80
     Abbiamo
    0.80
     allora
    0.78
     кожен
    0.78
    POSITIVE LOGITS
     necesita
    0.85
    тической
    0.78
     hidrat
    0.77
     desenc
    0.76
    ны
    0.76
     necesitan
    0.75
    ética
    0.75
     levantar
    0.75
     применяется
    0.73
     enfrenta
    0.73
    Act Density 0.000%

    No Known Activations