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

    Neuronpedia

    INDEX
    Explanations

    user tracking and event analytics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ังสือ
    0.42
     graphon
    0.42
     LANC
    0.42
    poetrylovers
    0.41
     алып
    0.41
    PLASMA
    0.40
    誦
    0.40
    CONSTRAINT
    0.40
    pastel
    0.39
    在外
    0.39
    POSITIVE LOGITS
     tracking
    1.19
    Tracking
    1.09
     Tracking
    1.09
     analytics
    1.03
     Analytics
    0.99
    tracking
    0.96
    Analytics
    0.94
     tracked
    0.93
    追踪
    0.92
    跟踪
    0.90
    Act Density 0.019%

    No Known Activations