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

    Neuronpedia

    INDEX
    Explanations

    sheet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rod
    -0.08
     Symfony
    -0.07
    فذ
    -0.07
    cod
    -0.07
    Hang
    -0.07
     الخي
    -0.07
    𝐗
    -0.07
    겊
    -0.07
    نسخ
    -0.07
    ти
    -0.07
    POSITIVE LOGITS
    balances
    0.08
     bracelets
    0.08
    َا
    0.07
     שם
    0.07
     mają
    0.07
    됩니다
    0.07
    _ISR
    0.07
     같
    0.07
     ownership
    0.07
     proponents
    0.06
    Act Density 0.001%

    No Known Activations