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

    Neuronpedia

    INDEX
    Explanations

    return 0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हमें
    0.41
    ilerini
    0.39
    ொள்ள
    0.38
    antar
    0.38
    क्ष्म
    0.38
    바로
    0.37
    ulton
    0.36
    kennt
    0.36
    鐫
    0.36
    Ident
    0.35
    POSITIVE LOGITS
     EXIT
    0.66
    EXIT
    0.66
     success
    0.62
     успеш
    0.62
    success
    0.61
     успешно
    0.59
     successful
    0.58
    Exit
    0.58
     SUCCESS
    0.58
     successo
    0.57
    Act Density 0.013%

    No Known Activations