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

    Neuronpedia

    INDEX
    Explanations

    one or single

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    carboxylate
    0.38
     préciser
    0.37
     Specifically
    0.37
    द्दल
    0.37
    حديد
    0.37
    ചന
    0.37
     nữa
    0.36
    ゔ
    0.36
     اخرى
    0.35
     تحديد
    0.35
    POSITIVE LOGITS
     single
    1.95
     ஒரே
    1.94
    单一
    1.88
    single
    1.77
    同一个
    1.72
    同一
    1.63
     SINGLE
    1.61
    单个
    1.60
    Single
    1.59
     еди
    1.55
    Act Density 0.075%

    No Known Activations