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

    Neuronpedia

    INDEX
    Explanations

    experimental or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pines
    0.48
     blobs
    0.47
     бит
    0.47
     tunnels
    0.45
     gute
    0.45
     այ
    0.44
     номина
    0.44
     是否
    0.43
     Можно
    0.43
     άλλα
    0.43
    POSITIVE LOGITS
    during
    0.52
    at
    0.48
     Celebr
    0.47
     celebr
    0.45
     Experimental
    0.43
    দ্ধ
    0.42
    अला
    0.42
     Alo
    0.41
    ارق
    0.41
    in
    0.40
    Act Density 0.001%

    No Known Activations