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

    Neuronpedia

    INDEX
    Explanations

    interaction and interconnectedness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     शार्
    0.47
    ല്ലാത്ത
    0.44
     skoro
    0.42
    を使用した
    0.42
     mainstay
    0.41
     মনির
    0.40
     शही
    0.39
     Accuracy
    0.38
     asegura
    0.38
     anbef
    0.37
    POSITIVE LOGITS
     interactions
    1.64
     Interactions
    1.50
     interaction
    1.49
    interactions
    1.48
    interaction
    1.39
     interacción
    1.34
     взаимодействие
    1.34
     INTERACTIONS
    1.33
     interacting
    1.32
     взаимодействия
    1.32
    Act Density 0.055%

    No Known Activations