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

    Neuronpedia

    INDEX
    Explanations

    living

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    546
    -0.06
    -manager
    -0.06
    odom
    -0.06
    ردد
    -0.06
     IEnumerable
    -0.06
    Raised
    -0.06
    unicorn
    -0.06
    录
    -0.06
    908
    -0.06
    (custom
    -0.06
    POSITIVE LOGITS
     Evans
    0.07
    _within
    0.07
     AGAIN
    0.07
    WITHOUT
    0.06
    alchemy
    0.06
    ."↵↵↵
    0.06
     теор
    0.06
     Alliance
    0.06
     multer
    0.06
    izing
    0.06
    Act Density 0.377%

    No Known Activations