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

    Neuronpedia

    INDEX
    Explanations

    borrowing and problem-solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informal
    0.41
     FACT
    0.41
    والفق
    0.41
     únic
    0.41
     Кор
    0.41
     Informal
    0.40
    ೕ
    0.39
    そこ
    0.39
    ﹂
    0.38
     -!
    0.38
    POSITIVE LOGITS
    house
    0.45
    borrow
    0.44
    mole
    0.41
    Borrowed
    0.41
     borrowed
    0.39
    ሕ
    0.38
     exogenous
    0.38
    eting
    0.37
     خانہ
    0.37
    apps
    0.37
    Act Density 0.001%

    No Known Activations