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

    Neuronpedia

    INDEX
    Explanations

    technical urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cristiana
    0.30
     turpentine
    0.29
     sauvage
    0.29
     sépar
    0.29
     crossbow
    0.29
     cuatro
    0.28
     cyst
    0.28
     lym
    0.28
     bốn
    0.28
     vegetable
    0.28
    POSITIVE LOGITS
    ด
    0.29
    ї
    0.27
    o
    0.26
    กด
    0.26
    ி
    0.26
    cı
    0.25
    த
    0.25
    那边
    0.25
    і
    0.24
    yal
    0.23
    Act Density 0.050%

    No Known Activations