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

    Neuronpedia

    INDEX
    Explanations

    demonstrating impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     для
    0.55
     لهذه
    0.54
     этому
    0.48
     แ
    0.48
    ഌ
    0.47
    讼
    0.46
     for
    0.45
     dedi
    0.43
     dédiée
    0.43
     thefe
    0.43
    POSITIVE LOGITS
    r
    0.50
    f
    0.48
    Wait
    0.48
    >\<^
    0.45
    Observers
    0.44
     Crusaders
    0.43
     Crude
    0.43
    Sentinel
    0.42
     Gladstone
    0.42
    FirstOrDefault
    0.41
    Act Density 0.004%

    No Known Activations