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

    Neuronpedia

    INDEX
    Explanations

    found it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thay
    0.49
    ווי
    0.47
    uci
    0.46
    ecia
    0.45
    kB
    0.45
     expériences
    0.45
    på
    0.44
     regenv
    0.44
    تھی
    0.44
    瑀
    0.44
    POSITIVE LOGITS
    中
    0.43
     Statue
    0.41
    ط
    0.40
     sive
    0.40
     detective
    0.39
     constitution
    0.39
    داشت
    0.38
     dynamically
    0.37
    مرين
    0.37
    آن
    0.37
    Act Density 0.001%

    No Known Activations