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

    Neuronpedia

    INDEX
    Explanations

    job, school, student, company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝓭
    0.91
    спублі
    0.76
    。『
    0.76
     tapi
    0.75
    。「
    0.75
     kilometres
    0.74
     altas
    0.74
    </em>
    0.73
    <0x83>
    0.73
    ;",
    0.73
    POSITIVE LOGITS
    و
    0.87
    ん
    0.86
     morphisms
    0.84
     যাদের
    0.80
    y
    0.79
    тся
    0.78
     Avoiding
    0.78
    Hvis
    0.75
    T
    0.75
    什麼
    0.74
    Act Density 0.045%

    No Known Activations