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

    Neuronpedia

    INDEX
    Explanations

    last resort options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inaugur
    0.40
     quirks
    0.38
     mos
    0.37
    领
    0.37
     preds
    0.35
     মুগ্ধ
    0.35
     delight
    0.35
    Guesses
    0.35
     знаходи
    0.34
    工夫
    0.33
    POSITIVE LOGITS
     option
    1.67
     opção
    1.49
    option
    1.43
     opción
    1.43
     Option
    1.37
     विकल्प
    1.37
    选项
    1.27
    選項
    1.27
    オプション
    1.19
     options
    1.17
    Act Density 0.013%

    No Known Activations