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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    そんな
    -0.07
     Loch
    -0.07
    ोस
    -0.07
     abdom
    -0.07
    _FIX
    -0.06
     Hàng
    -0.06
     riding
    -0.06
     refactor
    -0.06
     di
    -0.06
     companions
    -0.06
    POSITIVE LOGITS
     galleries
    0.07
     TForm
    0.06
    versions
    0.06
    MMdd
    0.06
    -module
    0.06
    .writerow
    0.06
    .createStatement
    0.06
     Russell
    0.06
     указ
    0.06
    усти
    0.06
    Act Density 0.042%

    No Known Activations