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

    Neuronpedia

    INDEX
    Explanations

    political events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     Subway
    -0.08
     camar
    -0.08
     penetr
    -0.07
     DY
    -0.07
     financier
    -0.07
     recruited
    -0.07
    (CONFIG
    -0.07
    �
    -0.06
              
↵
    -0.06
    POSITIVE LOGITS
     Authority
    0.08
     Bolt
    0.08
     Stud
    0.07
    视
    0.07
    面板
    0.07
    天花
    0.07
     Large
    0.07
     Limit
    0.07
     Lots
    0.06
     botanical
    0.06
    Act Density 0.069%

    No Known Activations