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

    Neuronpedia

    INDEX
    Explanations

    ogen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yup
    -0.08
     Yup
    -0.08
    vida
    -0.07
    .Parser
    -0.07
    褐色
    -0.07
    agner
    -0.07
     진행
    -0.07
     fragile
    -0.07
     marriages
    -0.07
     băng
    -0.07
    POSITIVE LOGITS
    ↵            
↵
    0.07
     עוב
    0.07
    0.07
     PD
    0.06
     IP
    0.06
    议员
    0.06
    地區
    0.06
     Enemy
    0.06
    尤其是
    0.06
     increasing
    0.06
    Act Density 0.001%

    No Known Activations