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

    Neuronpedia

    INDEX
    Explanations

    explanations and breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     homologs
    0.47
     welds
    0.47
     piglets
    0.45
    arey
    0.44
    znej
    0.43
     hypoxic
    0.43
     veal
    0.43
     monolayers
    0.43
     τ
    0.43
     ló
    0.42
    POSITIVE LOGITS
    ’
    0.48
    どんどん
    0.46
    </strong>
    0.44
    īt
    0.42
    </code>
    0.41
    ंपर्यंत
    0.39
    javascript
    0.38
    *
    0.38
    不断
    0.37
    ปัญหา
    0.37
    Act Density 0.001%

    No Known Activations