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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    1.55
     WTO
    1.49
     AB
    1.40
     CFT
    1.39
    Rpc
    1.39
     कि
    1.37
     SAT
    1.37
    м
    1.36
     АК
    1.36
     AZ
    1.35
    POSITIVE LOGITS
    s
    3.14
    l
    2.47
    ের
    2.29
    ्स
    2.17
    r
    1.98
    d
    1.98
    t
    1.96
    ことが多い
    1.70
    system
    1.70
    is
    1.69
    Act Density 0.311%

    No Known Activations