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

    Neuronpedia

    INDEX
    Explanations

    simple plans and physical qubits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ूतक
    0.48
    疖
    0.47
    tariff
    0.47
    िरण
    0.46
    痱
    0.46
     dozen
    0.46
     propriety
    0.45
    squre
    0.45
    歿
    0.44
     skrz
    0.44
    POSITIVE LOGITS
    OF
    0.50
     chỗ
    0.45
     compartir
    0.44
    Utils
    0.42
    (:
    0.41
    E
    0.41
     Dao
    0.40
    T
    0.40
    Untuk
    0.40
    創作
    0.40
    Act Density 0.002%

    No Known Activations