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

    Neuronpedia

    INDEX
    Explanations

    Sec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    정부
    -0.07
    -paid
    -0.07
     herself
    -0.07
    -driving
    -0.07
    创
    -0.07
     hallway
    -0.06
     attravers
    -0.06
     Москов
    -0.06
    ยว
    -0.06
    obbled
    -0.06
    POSITIVE LOGITS
    weighted
    0.06
    PHPExcel
    0.06
    0.06
    This
    0.06
    0.06
     réfé
    0.06
     CommandType
    0.06
     котором
    0.06
    0.06
    ':
↵
    0.06
    Act Density 0.003%

    No Known Activations