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

    Neuronpedia

    INDEX
    Explanations

    abstract nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoient
    -0.50
     abandonné
    -0.49
     câte
    -0.49
     quæ
    -0.49
     noires
    -0.48
     ainfi
    -0.48
     nicio
    -0.48
     feroit
    -0.47
    rungsseite
    -0.46
     picioare
    -0.45
    POSITIVE LOGITS
     Area
    1.15
     Movement
    1.09
     System
    1.09
     Region
    1.09
     Period
    1.08
     Sector
    1.06
     Concept
    1.06
     Process
    1.06
     Generation
    1.05
     Structure
    1.05
    Act Density 0.001%

    No Known Activations