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

    Neuronpedia

    INDEX
    Explanations

    responsibilities and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setStyleSheet
    1.07
    剂
    1.01
     slums
    0.97
    𝙴
    0.97
     numerals
    0.95
     toute
    0.95
    ⦁
    0.94
    רט
    0.93
    genus
    0.93
    MotionEvent
    0.92
    POSITIVE LOGITS
     tasks
    1.13
     Tasks
    1.04
     task
    0.98
     jawab
    0.97
    ty
    0.92
    f
    0.88
     responsibility
    0.85
     Aufgaben
    0.85
     behalf
    0.84
    既然
    0.83
    Act Density 0.140%

    No Known Activations