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

    Neuronpedia

    INDEX
    Explanations

    plant names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BIOS
    0.48
    动物
    0.44
     BIOS
    0.42
     СССР
    0.40
    生物
    0.40
     NPC
    0.40
    军队
    0.40
    ravariant
    0.39
    빚
    0.38
     IDs
    0.38
    POSITIVE LOGITS
     tomatoes
    1.22
     pineapple
    1.20
     lilies
    1.20
     blueberries
    1.18
     orchids
    1.17
     wheat
    1.16
     sunflowers
    1.16
     strawberries
    1.13
     roses
    1.11
     rosemary
    1.09
    Act Density 0.041%

    No Known Activations