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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    efficacité
    0.42
    Puedes
    0.41
     ermöglichen
    0.41
    возможно
    0.40
    פשר
    0.39
    immutable
    0.38
     possibilité
    0.38
    Concurrency
    0.38
    Aggregation
    0.38
     comprensión
    0.37
    POSITIVE LOGITS
     up
    0.64
     into
    0.60
     out
    0.57
     off
    0.49
     down
    0.46
     on
    0.44
     your
    0.43
     with
    0.42
     yourselves
    0.41
     yourself
    0.41
    Act Density 0.425%

    No Known Activations