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

    Neuronpedia

    INDEX
    Explanations

    BERT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.80
    ﺹ
    0.75
     calories
    0.73
    CH
    0.73
    PORT
    0.71
     Attempts
    0.71
     de
    0.70
    DE
    0.70
    TOP
    0.70
    カーテン
    0.70
    POSITIVE LOGITS
    asının
    0.80
    यण
    0.77
     влияет
    0.77
    я
    0.77
     conoce
    0.76
    려는
    0.76
     conocer
    0.75
     интеллектуа
    0.75
     चूंकि
    0.75
     lleva
    0.75
    Act Density 0.045%

    No Known Activations