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

    Neuronpedia

    INDEX
    Explanations

    etrain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    package
    -0.06
     convers
    -0.06
    dead
    -0.06
     alanında
    -0.06
    	offset
    -0.06
     липня
    -0.06
    =====↵
    -0.05
    Where
    -0.05
    difficulty
    -0.05
     ajust
    -0.05
    POSITIVE LOGITS
     deprived
    0.07
    \Seeder
    0.07
    ORITY
    0.07
     tương
    0.07
    clipse
    0.07
    팅
    0.06
    ś
    0.06
    (cluster
    0.06
    Important
    0.06
    _EMP
    0.06
    Act Density 0.400%

    No Known Activations