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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stringValue
    -0.06
    之一
    -0.06
     UserController
    -0.06
     dateString
    -0.06
    ]}"
    -0.06
     receipts
    -0.06
     возраста
    -0.06
     impending
    -0.06
    莫
    -0.06
    aviours
    -0.06
    POSITIVE LOGITS
     employment
    0.07
     Workplace
    0.07
     vend
    0.06
     --↵↵
    0.06
    /ay
    0.06
    �
    0.06
     QDialog
    0.06
    ávě
    0.06
     entertaining
    0.06
    ,**
    0.06
    Act Density 0.004%

    No Known Activations