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

    Neuronpedia

    INDEX
    Explanations

    calculus and code operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    నాలు
    0.43
     identifik
    0.41
     tuf
    0.40
    ufieurs
    0.39
     পোষ্ট
    0.37
     Những
    0.37
    лон
    0.37
     andRow
    0.37
    汙
    0.37
    োষণ
    0.36
    POSITIVE LOGITS
     Gandhi
    0.40
     tilbake
    0.37
     embarrassed
    0.35
     bre
    0.34
    க்கி
    0.34
     ze
    0.33
     dams
    0.33
     ద
    0.32
     Learned
    0.32
    Naive
    0.32
    Act Density 0.053%

    No Known Activations