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

    Neuronpedia

    INDEX
    Explanations

    operating performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.54
    le
    0.50
     eucalyptus
    0.48
     introduction
    0.46
     exhibition
    0.46
     Thames
    0.45
    ުޅ
    0.44
    Q
    0.43
     ocean
    0.43
     downstairs
    0.43
    POSITIVE LOGITS
     ترین
    0.55
     بە
    0.54
    toprule
    0.53
     vVertex
    0.52
    䏲
    0.52
    。
    0.50
    。\
    0.49
     ہے۔
    0.49
     हल्का
    0.48
    。</
    0.48
    Act Density 0.000%

    No Known Activations