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

    Neuronpedia

    INDEX
    Explanations

    developed by Gemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    齡
    0.37
    ändern
    0.37
    nodemailer
    0.37
     nodemailer
    0.36
    istencia
    0.34
    CharAt
    0.34
     мень
    0.34
    dataLayer
    0.34
     ഉള്‍
    0.34
    市值
    0.33
    POSITIVE LOGITS
    ફે
    0.42
    ي
    0.41
    asko
    0.39
    六
    0.39
    تف
    0.38
    즈
    0.37
     serviced
    0.37
     domu
    0.37
     도전
    0.37
    itzel
    0.37
    Act Density 0.001%

    No Known Activations