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

    Neuronpedia

    INDEX
    Explanations

    conduct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pers
    -0.07
     суп
    -0.07
    =time
    -0.06
    .Substring
    -0.06
    Ö
    -0.06
     zend
    -0.06
    sis
    -0.06
    飯
    -0.06
     فول
    -0.06
     august
    -0.06
    POSITIVE LOGITS
    ternal
    0.07
    (WIN
    0.06
    /us
    0.06
    ادل
    0.06
    conduct
    0.06
    人们
    0.06
     statues
    0.06
     enacted
    0.06
    "</
    0.06
     sacram
    0.06
    Act Density 0.004%

    No Known Activations