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

    Neuronpedia

    INDEX
    Explanations

    Taxonomy abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extradition
    -0.07
    ebx
    -0.07
    幡
    -0.07
    ߏ
    -0.07
    垴
    -0.07
     개
    -0.07
     UserDefaults
    -0.07
    徘
    -0.07
    .Diff
    -0.07
    สมา
    -0.07
    POSITIVE LOGITS
     today
    0.08
    _MODULE
    0.08
    _user
    0.07
     moderation
    0.07
    广东
    0.07
     Mike
    0.07
    .loader
    0.06
    .Column
    0.06
     lum
    0.06
    	c
    0.06
    Act Density 0.036%

    No Known Activations