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

    Neuronpedia

    INDEX
    Explanations

    Ok

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [...
    0.73
     _.
    0.72
     ***
    0.68
     keyst
    0.67
    .]:
    0.67
     라는
    0.65
     />;
    0.64
     株式会社
    0.62
     ሊ
    0.61
     |.
    0.61
    POSITIVE LOGITS
    Ok
    0.79
    Given
    0.72
    Being
    0.72
    Converting
    0.71
    Lors
    0.70
    Đối
    0.70
    Examples
    0.69
    Khi
    0.69
    接下來
    0.69
    ok
    0.69
    Act Density 0.377%

    No Known Activations