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

    Neuronpedia

    INDEX
    Explanations

    at the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    1.66
    ק
    1.59
    ৭
    1.56
    la
    1.50
    み
    1.49
    ৩
    1.47
     fibroblasts
    1.44
    ৮
    1.44
     zio
    1.42
    ५
    1.40
    POSITIVE LOGITS
    isiert
    1.54
     तौर
    1.52
    ্স
    1.48
    ités
    1.42
    тику
    1.42
    ă
    1.41
    깐
    1.41
    ઈ
    1.38
     allongé
    1.35
     Phần
    1.28
    Act Density 0.013%

    No Known Activations