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

    Neuronpedia

    INDEX
    Explanations

    Azure subscription

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    サー
    0.40
     Picks
    0.37
     games
    0.37
     BRAD
    0.37
     Pří
    0.36
    ind
    0.36
    avian
    0.36
    adventure
    0.35
    ambuf
    0.35
    alex
    0.35
    POSITIVE LOGITS
     पालक
    0.41
     cob
    0.41
     backgroundColor
    0.41
     режими
    0.40
     наблюда
    0.39
     родителей
    0.38
     lúc
    0.38
     Cob
    0.38
     fundamento
    0.38
    宰
    0.37
    Act Density 0.000%

    No Known Activations