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

    Neuronpedia

    INDEX
    Explanations

    San Francisco

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensibility
    0.39
    Multiple
    0.39
     restructure
    0.38
    Tmp
    0.37
     ವಿಶ
    0.37
     rostro
    0.37
    Merge
    0.37
    組み合わせ
    0.37
    σουμε
    0.37
    Sensor
    0.36
    POSITIVE LOGITS
     Aktien
    0.49
    夲
    0.44
     அறிமுக
    0.43
     поддержку
    0.43
     حول
    0.42
     Loves
    0.42
     फ्रांस
    0.41
     FACTS
    0.41
     nicknamed
    0.41
     bienvenidas
    0.41
    Act Density 0.000%

    No Known Activations