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

    Neuronpedia

    INDEX
    Explanations

    fun contexts and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    N
    1.14
     It
    1.07
    F
    1.03
    I
    1.00
    K
    0.91
    Fitness
    0.86
    Optimization
    0.86
    X
    0.85
    Quality
    0.85
     If
    0.83
    POSITIVE LOGITS
    ید
    0.98
    ية
    0.93
    ado
    0.91
     divertido
    0.88
    ك
    0.86
    ้ง
    0.84
    تي
    0.84
     constructively
    0.84
     fun
    0.82
    乐趣
    0.82
    Act Density 0.014%

    No Known Activations