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

    Neuronpedia

    INDEX
    Explanations

    multitasking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.53
    ED
    0.53
     কমল
    0.52
     트리플
    0.50
    중
    0.50
     צ
    0.49
    내
    0.49
    ى
    0.49
     بلکه
    0.48
    偻
    0.48
    POSITIVE LOGITS
    klahoma
    0.59
    Muh
    0.49
    si
    0.48
    ynchronous
    0.48
     обеспечи
    0.46
    ”，
    0.46
     in
    0.45
    tts
    0.45
     vilket
    0.44
    Houston
    0.44
    Act Density 0.001%

    No Known Activations