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

    Neuronpedia

    INDEX
    Explanations

    I understand and will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brauchen
    0.46
    need
    0.45
     necesitan
    0.45
     trochę
    0.45
     verschill
    0.44
     need
    0.44
     behöver
    0.41
    知道
    0.41
     किशन
    0.41
     പക്ഷേ
    0.41
    POSITIVE LOGITS
    ία
    0.39
     अवश्य
    0.39
     Bibliography
    0.38
     Examination
    0.38
     concludes
    0.38
     opting
    0.38
     concluding
    0.37
    を参照
    0.37
    C
    0.37
     Wonderland
    0.35
    Act Density 0.001%

    No Known Activations