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

    Neuronpedia

    INDEX
    Explanations

    show me * giving to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ihre
    0.46
     meine
    0.41
     ผม
    0.40
    ULT
    0.40
    gesetzt
    0.39
     آہ
    0.39
     UM
    0.37
     meinen
    0.37
    न्छ
    0.37
     UNO
    0.36
    POSITIVE LOGITS
     ему
    0.49
     لهم
    0.48
     ї
    0.46
     ihm
    0.42
     ihnen
    0.40
     તેમને
    0.40
     njemu
    0.40
    에게
    0.39
     ей
    0.39
     ಅವರಿಗೆ
    0.37
    Act Density 0.013%

    No Known Activations