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

    Neuronpedia

    INDEX
    Explanations

    code and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DLL
    0.57
     dll
    0.55
    dll
    0.44
     tray
    0.41
    DLL
    0.39
    Dll
    0.39
     "
    0.38
    ್ಣ
    0.38
     MessageBox
    0.38
    Ming
    0.38
    POSITIVE LOGITS
    ('/
    0.48
     (/
    0.42
     `/
    0.40
    慚
    0.38
     کرام
    0.37
    +'/
    0.36
    ("/
    0.36
     fibr
    0.36
    (`/
    0.36
    artan
    0.36
    Act Density 0.042%

    No Known Activations