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

    Neuronpedia

    INDEX
    Explanations

    translations and foreign language phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⃣
    0.42
    🔽
    0.41
     profit
    0.38
    👇
    0.36
     👇
    0.36
     anaer
    0.35
     medically
    0.35
     Mak
    0.35
     méthodique
    0.35
    곸
    0.35
    POSITIVE LOGITS
    翻译
    0.79
     yani
    0.71
    Translation
    0.70
     यानी
    0.69
     translates
    0.68
     ("
    0.67
    ("
    0.67
     translated
    0.64
     Translated
    0.64
    翻譯
    0.63
    Act Density 0.171%

    No Known Activations