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

    Neuronpedia

    INDEX
    Explanations

    how we can proceed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    讨论
    0.51
    discussion
    0.51
     discussão
    0.50
     debate
    0.49
     Diskussion
    0.49
     discussions
    0.47
     discusión
    0.47
     आपस
    0.47
     이야기를
    0.47
     debated
    0.46
    POSITIVE LOGITS
     interactivity
    0.55
     আমি
    0.54
     interactive
    0.49
     transact
    0.48
     سعر
    0.47
     interaction
    0.47
    আমি
    0.47
     Interaction
    0.47
     నాకు
    0.46
    互動
    0.46
    Act Density 0.028%

    No Known Activations