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

    Neuronpedia

    INDEX
    Explanations

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    2.02
    al
    1.95
    o
    1.88
    a
    1.75
    aing
    1.70
    ”
    1.70
    ot
    1.66
    q
    1.64
    er
    1.63
    ר
    1.63
    POSITIVE LOGITS
    ों
    1.80
    ের
    1.58
    ьте
    1.47
    此之外
    1.45
     dahulu
    1.42
    ്ട
    1.37
    ました
    1.34
    负责人
    1.34
     имущества
    1.34
    ገልግሎ
    1.34
    Act Density 0.033%

    No Known Activations