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

    Neuronpedia

    INDEX
    Explanations

    Summary, assignee, labels, test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tasks
    0.44
     समस्याओं
    0.43
     задач
    0.41
    任務
    0.41
     complaints
    0.40
     Lom
    0.40
     repairs
    0.40
     úlo
    0.39
     incidents
    0.38
     chores
    0.38
    POSITIVE LOGITS
    Summary
    0.64
    Attachments
    0.63
     assignee
    0.61
     Summary
    0.60
    Attachment
    0.60
     attachments
    0.58
     attachment
    0.58
     summary
    0.57
    summary
    0.56
    attachments
    0.56
    Act Density 0.015%

    No Known Activations