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

    Neuronpedia

    INDEX
    Explanations

    instruction phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     به‌عنوان
    0.61
    🌚
    0.57
     हेतु
    0.57
    ➡️
    0.53
    👌
    0.53
    🏞
    0.53
    😌
    0.52
    📝
    0.52
    🚫
    0.52
    🔛
    0.52
    POSITIVE LOGITS
     nto
    0.58
     teh
    0.52
     someth
    0.50
    떄
    0.49
     mogli
    0.48
     solve
    0.46
     lets
    0.46
     corret
    0.46
     allong
    0.45
     ignore
    0.45
    Act Density 0.009%

    No Known Activations