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

    Neuronpedia

    INDEX
    Explanations

    definition expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نہایت
    0.42
     itse
    0.40
     paroi
    0.39
    俗
    0.38
    ଗ
    0.38
     Bookstore
    0.38
     بالکل
    0.37
    的研究
    0.36
     ricerche
    0.36
     Marie
    0.36
    POSITIVE LOGITS
     royals
    0.49
     ancestors
    0.46
    blings
    0.46
     expuls
    0.45
     shenanigans
    0.44
     proteins
    0.44
     იქნება
    0.43
     progressions
    0.42
     priors
    0.42
     penguins
    0.42
    Act Density 0.002%

    No Known Activations