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

    Neuronpedia

    INDEX
    Explanations

    comparing features in tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.24
    as
    1.17
    el
    1.04
    elem
    1.02
    es
    0.95
    ed
    0.92
    ness
    0.89
    after
    0.89
    an
    0.81
     vit
    0.79
    POSITIVE LOGITS
    ösung
    1.05
    änen
    1.02
    äänt
    1.01
    ään
    1.00
    nění
    0.98
    ügel
    0.98
    ující
    0.98
    ésar
    0.97
     JsonConvert
    0.97
    uların
    0.97
    Act Density 0.070%

    No Known Activations