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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (interval
    -0.07
     там
    -0.06
     상세
    -0.06
     plane
    -0.06
    	system
    -0.06
    bersome
    -0.06
     Plane
    -0.06
    .fm
    -0.06
     praise
    -0.06
    Mounted
    -0.06
    POSITIVE LOGITS
     RequestMethod
    0.07
    ";"
    0.07
     ό
    0.07
     scenes
    0.07
    ських
    0.06
    ach
    0.06
     Sach
    0.06
    ागत
    0.06
     од
    0.06
    .MoveNext
    0.06
    Act Density 0.077%

    No Known Activations