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

    Neuronpedia

    INDEX
    Explanations

    database configuration commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     T
    0.39
     Fourth
    0.39
     Tell
    0.38
     ४
    0.38
     Lob
    0.37
     Tried
    0.37
     Pal
    0.37
     TBS
    0.37
     Shout
    0.37
     Bandit
    0.37
    POSITIVE LOGITS
    ={{
    0.46
     सम्पन्न
    0.46
    遏
    0.44
    സമ
    0.42
    தேச
    0.41
    =@@
    0.40
    CHECKS
    0.39
    themem
    0.39
     मोड
    0.39
    ModeBanner
    0.39
    Act Density 0.001%

    No Known Activations