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

    Neuronpedia

    INDEX
    Explanations

    current date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     novelists
    1.02
     novels
    0.81
     जून
    0.80
     июня
    0.79
     activists
    0.76
     July
    0.71
     novelist
    0.71
     month
    0.70
     June
    0.70
     ২০১৩
    0.70
    POSITIVE LOGITS
    🩶
    0.92
     danas
    0.88
    🩷
    0.78
     υψη
    0.77
     정리
    0.74
     faltando
    0.74
     ChatGPT
    0.73
     снижение
    0.73
    🫂
    0.72
    ChatGPT
    0.72
    Act Density 0.141%

    No Known Activations