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

    Neuronpedia

    INDEX
    Explanations

    technical descriptors and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಅ
    0.50
    ஐ
    0.50
     of
    0.49
     của
    0.48
    ೋ
    0.48
    新型コロナ
    0.46
    ಮ
    0.46
    ใน
    0.45
     îi
    0.44
    在
    0.44
    POSITIVE LOGITS
    un
    0.46
    Transactions
    0.44
    FER
    0.43
    usr
    0.43
    LER
    0.43
     banker
    0.42
     Hitachi
    0.42
    FL
    0.42
     surveyor
    0.40
    MULTI
    0.40
    Act Density 0.371%

    No Known Activations