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

    Neuronpedia

    INDEX
    Explanations

    assisting with tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permiss
    0.43
     interconnected
    0.41
     pathogenesis
    0.41
     viciss
    0.41
    sailboat
    0.41
     autorità
    0.40
     jurisdict
    0.39
    acquired
    0.38
     decisão
    0.38
    modus
    0.38
    POSITIVE LOGITS
     Assist
    0.78
     assist
    0.74
    帮忙
    0.70
    Assist
    0.68
     tasks
    0.66
     cleaning
    0.66
     Tasks
    0.66
     Assists
    0.65
     βοη
    0.65
     asist
    0.64
    Act Density 0.154%

    No Known Activations