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

    Neuronpedia

    INDEX
    Explanations

    homework and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.74
    。
    0.73
     in
    0.73
    .
    0.70
    在
    0.66
    我
    0.64
    à
    0.63
    ।
    0.62
    就
    0.60
    <0xB1>
    0.59
    POSITIVE LOGITS
    n
    1.00
     Homework
    0.86
     homework
    0.85
    i
    0.83
    as
    0.82
    ir
    0.82
     embank
    0.82
     ஃப
    0.79
    ي
    0.77
     Пра
    0.75
    Act Density 0.005%

    No Known Activations