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

    Neuronpedia

    INDEX
    Explanations

    health, speed, businesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Play
    0.25
     I
    0.24
    ト
    0.24
    LO
    0.24
    ↵↵
    0.23
     Net
    0.23
     Essays
    0.23
     ।
    0.23
     ת
    0.23
    सच
    0.23
    POSITIVE LOGITS
     clergyman
    0.27
    NuGetPackage
    0.25
    лыми
    0.24
     ئۇ
    0.24
     governo
    0.23
     юриди
    0.23
    ຢູ່ໃນ
    0.23
     kabupaten
    0.23
     Министерство
    0.23
    тором
    0.23
    Act Density 0.000%

    No Known Activations