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

    Neuronpedia

    INDEX
    Explanations

    drift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    惑
    -0.07
    崶
    -0.07
    팼
    -0.07
     explicit
    -0.07
    .Resume
    -0.07
     OU
    -0.07
    쌉
    -0.06
    kaza
    -0.06
    予
    -0.06
     /*!↵
    -0.06
    POSITIVE LOGITS
     사람들이
    0.08
     drifting
    0.08
    因为他们
    0.08
     Trucks
    0.07
    Fly
    0.07
    ointments
    0.07
    Dependencies
    0.07
     "','"
    0.07
     linguistic
    0.07
     التربية
    0.07
    Act Density 0.003%

    No Known Activations