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

    Neuronpedia

    INDEX
    Explanations

    musical arrangements and orchestration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </th>
    0.55
    </h2>
    0.54
     সিগারেট
    0.52
     aislamiento
    0.49
     lipstick
    0.49
     সিল
    0.49
     slang
    0.49
    lega
    0.48
    Refrigerator
    0.48
    …]
    0.48
    POSITIVE LOGITS
    、
    0.76
     Orche
    0.63
    （
    0.61
    (
    0.61
     (
    0.60
    ，
    0.60
    ブ
    0.59
     orchestr
    0.58
     =
    0.56
     الرا
    0.56
    Act Density 0.013%

    No Known Activations