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

    Neuronpedia

    INDEX
    Explanations

    benefits and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рто
    0.37
     sensory
    0.36
     reg
    0.36
     gede
    0.35
     toj
    0.34
    ixe
    0.34
     usual
    0.33
     படிக்க
    0.33
    ])$.
    0.33
     სახელმწიფ
    0.33
    POSITIVE LOGITS
    сцю
    0.41
    权益
    0.39
    ពណ៌
    0.39
    ്ല
    0.38
    moires
    0.38
     franchisees
    0.38
    뚝
    0.38
    льня
    0.38
     ціка
    0.37
    🚗
    0.37
    Act Density 0.000%

    No Known Activations