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

    Neuronpedia

    INDEX
    Explanations

    perform well or poorly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spécialistes
    0.46
     পাঁচটি
    0.42
     главных
    0.42
     même
    0.41
     fondamental
    0.40
    σκε
    0.39
     svých
    0.39
     gacche
    0.39
     sart
    0.39
     élargies
    0.39
    POSITIVE LOGITS
    گز
    0.44
     compelled
    0.38
     unable
    0.38
    翼
    0.36
    гло
    0.36
     incapable
    0.36
    度
    0.36
     emerges
    0.36
     haunted
    0.35
    ძ
    0.35
    Act Density 0.000%

    No Known Activations