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

    Neuronpedia

    INDEX
    Explanations

    gathering items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calves
    0.40
     puffs
    0.35
     pasture
    0.35
     callus
    0.33
     dressings
    0.33
     blisters
    0.33
     saliva
    0.32
     breasts
    0.32
     roast
    0.32
     vegetative
    0.32
    POSITIVE LOGITS
     دیجیت
    0.38
     Использу
    0.34
    ۔
    0.34
     აღმასრულებელი
    0.33
    Node
    0.32
    िओ
    0.32
    ейчас
    0.32
     estadounidense
    0.32
     ентите
    0.31
     چاہتے
    0.31
    Act Density 0.000%

    No Known Activations