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

    Neuronpedia

    INDEX
    Explanations

    less formal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cysteine
    0.79
     கண்டுபி
    0.78
    Ẻ
    0.76
     metabolized
    0.76
    摊
    0.74
     காமெடி
    0.74
    漏洞
    0.73
     প্রবৃত্ত
    0.73
    Cheap
    0.73
    🏄
    0.73
    POSITIVE LOGITS
     formal
    3.36
     Formal
    3.09
    Formal
    3.04
    formal
    3.00
     formality
    2.70
     ceremonial
    2.61
     ceremony
    2.59
     औपचारिक
    2.58
     formally
    2.57
     ceremonies
    2.46
    Act Density 0.467%

    No Known Activations