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

    Neuronpedia

    INDEX
    Explanations

    newline character following descriptive text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.41
     August
    0.41
    indow
    0.36
     ');
    0.35
     Aug
    0.35
     हीरा
    0.35
    watt
    0.35
     ",
    0.34
     ");
    0.34
    </div>
    0.34
    POSITIVE LOGITS
    "+"
    0.46
    Ɲ
    0.45
    ため
    0.45
    đe
    0.44
     मोस्ट
    0.44
    ستي
    0.44
     പറയ
    0.42
    などは
    0.42
    说说
    0.42
    閬
    0.41
    Act Density 0.006%

    No Known Activations