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

    Neuronpedia

    INDEX
    Explanations

    personal learning and tastes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    괜
    0.46
    🌬
    0.41
    🥲
    0.41
     रही
    0.41
    eniu
    0.41
    اپنی
    0.41
    🫤
    0.41
    픔
    0.40
     فريبي
    0.40
     प्रतिभागियों
    0.40
    POSITIVE LOGITS
     destructor
    0.44
    λος
    0.43
    iostream
    0.40
     List
    0.38
     editorial
    0.38
     interloc
    0.37
    FCO
    0.37
    belongs
    0.37
    嬷
    0.37
    ٬
    0.36
    Act Density 0.000%

    No Known Activations