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

    Neuronpedia

    INDEX
    Explanations

    scalability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    1.10
    ار
    1.09
    Millions
    1.07
    જનો
    1.05
     userID
    1.04
    ंग
    1.02
    🧉
    1.01
     FEC
    1.01
    রাদ
    1.00
    csdn
    0.99
    POSITIVE LOGITS
    ция
    1.13
    л
    1.11
    voje
    1.05
    ায়ার
    1.04
    牘
    0.96
     naik
    0.95
     पैमाने
    0.94
    砣
    0.93
    aborasi
    0.93
     débit
    0.93
    Act Density 0.069%

    No Known Activations