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

    Neuronpedia

    INDEX
    Explanations

    time or start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ])){
    1.05
     whereabouts
    0.97
    我和
    0.97
     reasons
    0.94
    其
    0.93
     CVE
    0.93
     fences
    0.92
     waterfalls
    0.92
    Acts
    0.92
    আমি
    0.91
    POSITIVE LOGITS
     bör
    1.18
     både
    1.18
     wanneer
    1.17
     angin
    1.17
    ienst
    1.17
     først
    1.17
     Eğer
    1.16
     før
    1.10
     kalangan
    1.08
     सर्वप्रथम
    1.08
    Act Density 0.002%

    No Known Activations