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

    Neuronpedia

    INDEX
    Explanations

    hardware, Python, management, recognition script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astrar
    0.43
     Nothing
    0.41
    尽管
    0.40
     seda
    0.38
     никаких
    0.38
     -=
    0.37
     DNN
    0.37
     logika
    0.37
     ladr
    0.36
     मोस्ट
    0.36
    POSITIVE LOGITS
    グレード
    0.41
     adviser
    0.37
     designee
    0.37
     packs
    0.35
     enhancements
    0.33
     coordinator
    0.33
     Advisor
    0.32
     enhancer
    0.32
     entitlements
    0.32
     guide
    0.31
    Act Density 0.084%

    No Known Activations