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

    Neuronpedia

    INDEX
    Explanations

    regex patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -"
    0.50
     फेक
    0.48
     another
    0.47
     phantom
    0.43
     गोष्ट
    0.43
     -
    0.43
    ộn
    0.42
     menjalankan
    0.42
     penting
    0.42
    のこと
    0.42
    POSITIVE LOGITS
     কোনো
    0.59
    ANY
    0.58
    Delimiter
    0.58
    ﻤ
    0.57
    Any
    0.56
    任何
    0.56
     कोई
    0.56
     ഏത
    0.56
     Далее
    0.55
    any
    0.54
    Act Density 0.035%

    No Known Activations