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

    Neuronpedia

    INDEX
    Explanations

    illegal activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     giochi
    0.45
    ṱ
    0.43
     CHANNEL
    0.42
     Jenis
    0.42
     Kees
    0.40
    الك
    0.39
     sights
    0.39
     পুস্ত
    0.39
     परिचाल
    0.39
     heed
    0.38
    POSITIVE LOGITS
     entirely
    0.40
    পে
    0.39
     потреб
    0.38
    वून
    0.37
     nuggets
    0.37
    ডের
    0.37
    伐
    0.36
     совсем
    0.36
    amazon
    0.35
     جهد
    0.35
    Act Density 0.001%

    No Known Activations