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

    Neuronpedia

    INDEX
    Explanations

    academic, religious, training, rebuilding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ต้า
    0.47
    四川
    0.45
    くれる
    0.43
     décadas
    0.42
     दशकों
    0.42
     startet
    0.42
    કારે
    0.42
    喺
    0.41
    व्ही
    0.41
     könnt
    0.40
    POSITIVE LOGITS
    竞争力
    0.46
     a
    0.46
    。
    0.43
     an
    0.43
    ।
    0.43
    .”
    0.42
     something
    0.42
     its
    0.41
     any
    0.41
     itself
    0.41
    Act Density 0.009%

    No Known Activations