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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perk
    -0.07
    讯
    -0.06
     stu
    -0.06
     entire
    -0.06
     shoppers
    -0.06
    bac
    -0.06
    submit
    -0.06
     brass
    -0.06
     localized
    -0.06
    着
    -0.06
    POSITIVE LOGITS
    _DEV
    0.06
    upported
    0.06
     elektr
    0.06
     �
    0.06
     Мал
    0.06
     İmparator
    0.06
     아닌
    0.06
     Measure
    0.06
    	Namespace
    0.06
     Stmt
    0.06
    Act Density 0.036%

    No Known Activations