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

    Neuronpedia

    INDEX
    Explanations

    as for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     someone
    0.81
     gardeners
    0.75
     often
    0.74
     providers
    0.74
     especially
    0.73
     screws
    0.72
     flips
    0.72
     souvent
    0.71
     tosses
    0.71
     adults
    0.71
    POSITIVE LOGITS
    for
    2.05
     for
    1.87
     для
    1.81
    For
    1.74
    для
    1.55
    Для
    1.46
     für
    1.43
    FOR
    1.43
     برای
    1.41
     For
    1.41
    Act Density 0.009%

    No Known Activations