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

    Neuronpedia

    INDEX
    Explanations

    data manipulation and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     analytics
    0.49
    newdata
    0.46
     Analytics
    0.45
    punkte
    0.45
     analytic
    0.45
     privacy
    0.44
     analytical
    0.43
    lllll
    0.43
     telemetry
    0.42
     데이터
    0.41
    POSITIVE LOGITS
    frames
    0.43
    Frames
    0.43
    모델
    0.42
     köt
    0.41
     wr
    0.41
     ma
    0.40
     Structures
    0.40
    Structures
    0.40
    שא
    0.39
    க்த
    0.38
    Act Density 0.025%

    No Known Activations