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

    Neuronpedia

    INDEX
    Explanations

    is powerful, been compiling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yar
    0.38
     मध्या
    0.38
     insist
    0.37
     δὲ
    0.37
     Mij
    0.37
    uitary
    0.36
     Lodge
    0.36
    വിത
    0.36
     Srbiji
    0.36
     final
    0.36
    POSITIVE LOGITS
     TypeError
    0.42
    ܡ
    0.39
    ecommerce
    0.39
    恩
    0.38
     কুম
    0.38
    เภท
    0.38
    률
    0.38
    গ্ন
    0.37
     топ
    0.37
    ékony
    0.36
    Act Density 0.000%

    No Known Activations