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

    Neuronpedia

    INDEX
    Explanations

    Python, Langchain, Tkinter, Lua, QA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    €™
    1.78
    وی
    1.60
    ip
    1.56
    kb
    1.55
    kj
    1.53
    Р
    1.52
    UT
    1.49
    buat
    1.48
    codec
    1.46
    city
    1.45
    POSITIVE LOGITS
     adage
    1.76
     appe
    1.56
     a
    1.54
     bart
    1.54
     viv
    1.51
     souvenirs
    1.51
     l
    1.48
     vicious
    1.48
     stup
    1.47
     scr
    1.46
    Act Density 0.050%

    No Known Activations