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

    Neuronpedia

    INDEX
    Explanations

    named entities and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    0.92
    quakes
    0.91
    e
    0.90
    𝙨
    0.87
    िया
    0.86
    ार्थी
    0.85
    িয়া
    0.85
    ین
    0.84
    ья
    0.81
    पालिका
    0.81
    POSITIVE LOGITS
    3
    1.20
    1
    1.11
    7
    1.11
    4
    1.05
     Issled
    1.00
    0
    1.00
     zalo
    0.99
     искусства
    0.96
     photographers
    0.96
    5
    0.96
    Act Density 0.276%

    No Known Activations