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

    Neuronpedia

    INDEX
    Explanations

    code syntax and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ح
    1.65
    ﾟ
    1.48
    ﻟ
    1.47
    spending
    1.46
    tied
    1.45
    ained
    1.43
    す
    1.42
    ्ड
    1.41
    醯
    1.40
    scapes
    1.38
    POSITIVE LOGITS
     Anschließend
    2.19
     große
    2.14
     Еще
    2.00
    Еще
    1.84
    ان
    1.82
     এছাড়াও
    1.79
     régionale
    1.76
     flavored
    1.74
     الخارج
    1.73
     schließlich
    1.70
    Act Density 0.068%

    No Known Activations