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

    Neuronpedia

    INDEX
    Explanations

    some are starting to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    1.18
    ll
    1.13
    л
    1.13
    к
    1.11
     a
    1.05
    ard
    1.03
    лі
    0.99
    ز
    0.97
     probably
    0.95
     about
    0.95
    POSITIVE LOGITS
     honti
    1.22
     ribu
    1.15
     SPMs
    1.05
     thermoplastics
    1.03
     amelyek
    1.02
    prits
    0.98
    硗
    0.97
    暊
    0.96
     vacanam
    0.95
     pabbaj
    0.95
    Act Density 0.191%

    No Known Activations