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

    Neuronpedia

    INDEX
    Explanations

    rules or instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Auch
    -0.07
    'A
    -0.06
    为什么
    -0.06
     Knife
    -0.06
     подой
    -0.06
     scored
    -0.06
    [['
    -0.06
     Pic
    -0.06
     SMS
    -0.06
    'D
    -0.06
    POSITIVE LOGITS
    COOKIE
    0.07
    ционные
    0.07
     शक
    0.07
    ConnectionFactory
    0.06
     anterior
    0.06
     headline
    0.06
    lín
    0.06
    ์การ
    0.06
     shards
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations