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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     میک
    -0.07
     schwar
    -0.06
     deutschland
    -0.06
    (transaction
    -0.06
     headphones
    -0.06
    ское
    -0.06
    unread
    -0.06
     né
    -0.05
    нюю
    -0.05
     دانشجوی
    -0.05
    POSITIVE LOGITS
     Elim
    0.07
     활동
    0.07
    าคาร
    0.07
    ��
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    COMMAND
    0.06
    ΗΡ
    0.06
     Voll
    0.06
     convened
    0.06
    بيع
    0.06
    Act Density 0.009%

    No Known Activations