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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Passport
    -0.06
     sign
    -0.06
    ǎ
    -0.06
     استخدام
    -0.06
    θήκη
    -0.06
    нез
    -0.06
    /arch
    -0.06
     Prel
    -0.06
    بدأ
    -0.06
     meddling
    -0.06
    POSITIVE LOGITS
     artık
    0.06
     şehir
    0.06
     (--
    0.06
    SPA
    0.06
    "https
    0.06
     تیم
    0.06
     mysl
    0.06
     인간
    0.06
    �
    0.06
     biraz
    0.06
    Act Density 0.035%

    No Known Activations