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

    Neuronpedia

    INDEX
    Explanations

    country names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CONTROL
    -0.07
    wallet
    -0.07
    released
    -0.07
    �
    -0.07
    raz
    -0.06
     Control
    -0.06
    Mah
    -0.06
    arrass
    -0.06
     buff
    -0.06
    regulated
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ุงเทพ
    0.06
    QUIRED
    0.06
     προς
    0.06
     موفق
    0.06
     vysvět
    0.06
    Не
    0.06
     инвести
    0.06
    ιλο
    0.06
     Doğu
    0.06
    Act Density 0.056%

    No Known Activations