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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সমস্যা
    0.41
     परेशानी
    0.40
     அதிகரிக்க
    0.40
     otoño
    0.40
    แป
    0.39
     இட
    0.39
     фараз
    0.39
     অবহিত
    0.38
    AIM
    0.38
     ಸರಿಯ
    0.38
    POSITIVE LOGITS
    signUp
    0.46
    ربه
    0.38
    رب
    0.37
     roman
    0.37
     belief
    0.37
    idential
    0.37
     Em
    0.36
    Em
    0.36
    ButtonStyle
    0.35
     signUp
    0.35
    Act Density 0.001%

    No Known Activations