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

    Neuronpedia

    INDEX
    Explanations

    Business-related topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fool
    -0.07
    과
    -0.06
     docs
    -0.06
     RSA
    -0.06
     triangles
    -0.06
     colleges
    -0.06
    _SCAN
    -0.06
     Stern
    -0.06
     TEXT
    -0.06
     Center
    -0.06
    POSITIVE LOGITS
     bekl
    0.07
     чуть
    0.07
    ↵
↵
↵
    0.07
     дов
    0.06
    応
    0.06
    จำหน
    0.06
    镜
    0.06
     провер
    0.06
    Cooldown
    0.06
     málo
    0.06
    Act Density 0.007%

    No Known Activations