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

    Neuronpedia

    INDEX
    Explanations

    GUI designers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.64
    あなたは
    0.64
    자
    0.61
    ła
    0.59
     by
    0.59
    ی
    0.56
     Abbiamo
    0.56
    你
    0.54
    あなたが
    0.53
    ऊदी
    0.52
    POSITIVE LOGITS
     voorkomen
    0.59
     heats
    0.57
    CLOS
    0.53
    िन
    0.52
    гти
    0.52
     chung
    0.49
    क्ल
    0.49
     nhấn
    0.49
     lợi
    0.49
     комплекса
    0.48
    Act Density 0.000%

    No Known Activations