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

    Neuronpedia

    INDEX
    Explanations

    be warned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ży
    0.46
    aken
    0.46
    pic
    0.45
    ́p
    0.45
    pill
    0.44
    ń
    0.44
    dit
    0.43
    ub
    0.42
    uis
    0.42
    5
    0.41
    POSITIVE LOGITS
    钬
    0.46
    该
    0.44
    抵
    0.43
    AutoStabilise
    0.42
     indebtedness
    0.42
     Subway
    0.42
     该
    0.42
     insurrection
    0.42
     IRB
    0.42
     Honolulu
    0.41
    Act Density 0.010%

    No Known Activations