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

    Neuronpedia

    INDEX
    Explanations

    genealogy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Creat
    -0.07
     Bunifu
    -0.07
    day
    -0.07
     wreak
    -0.07
     Drill
    -0.06
     beds
    -0.06
     angel
    -0.06
    乙
    -0.06
     heart
    -0.06
    ball
    -0.06
    POSITIVE LOGITS
     augmented
    0.07
    ):
↵
↵
    0.07
    Ï
    0.06
    ildiği
    0.06
     lineage
    0.06
     valeur
    0.06
     IR
    0.06
     индивиду
    0.06
     jinak
    0.06
    џџџ
    0.06
    Act Density 0.012%

    No Known Activations