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

    Neuronpedia

    INDEX
    Explanations

    C# code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moest
    1.54
     způ
    1.52
    궪
    1.52
    িগ্ন
    1.49
     exemplifies
    1.47
    एको
    1.47
     الاجتماعي
    1.45
     sigurn
    1.45
     ucap
    1.44
    embourg
    1.43
    POSITIVE LOGITS
    大
    1.43
    ب
    1.43
    आप
    1.41
    it
    1.39
    好
    1.37
    其
    1.34
    ગુ
    1.33
    ant
    1.33
     Drosophila
    1.33
    ch
    1.31
    Act Density 0.001%

    No Known Activations