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

    Neuronpedia

    INDEX
    Explanations

    end of factual statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    0.80
     مثلا
    0.78
    等地
    0.77
    さり
    0.73
    範
    0.73
    যেমন
    0.72
     وغیرہ
    0.71
    ང
    0.71
     Etc
    0.70
     इत्यादी
    0.70
    POSITIVE LOGITS
     Thats
    1.09
    其中包括
    0.99
     suddiv
    0.94
     Considerando
    0.93
     आंकड़ा
    0.92
     répart
    0.90
     waarvan
    0.90
     That
    0.90
    That
    0.89
     Compared
    0.87
    Act Density 0.686%

    No Known Activations