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

    Neuronpedia

    INDEX
    Explanations

    school and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     в
    0.61
     in
    0.45
    在
    0.42
     \
    0.41
    L
    0.40
     Р
    0.39
    ส
    0.39
     σε
    0.38
     aerobics
    0.38
    我们
    0.38
    POSITIVE LOGITS
    u
    0.47
    ږئ
    0.43
    i
    0.42
    line
    0.39
    טה
    0.38
    y
    0.38
    day
    0.37
    ON
    0.36
     sasane
    0.36
     داله
    0.36
    Act Density 0.003%

    No Known Activations