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

    Neuronpedia

    INDEX
    Explanations

    Proper sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SID
    -0.07
     GDK
    -0.06
    defer
    -0.06
     LOD
    -0.06
    廣
    -0.06
    Orders
    -0.06
    ό
    -0.06
     bekom
    -0.06
    MP
    -0.06
     devotion
    -0.06
    POSITIVE LOGITS
    obody
    0.07
     России
    0.07
     آموزش
    0.07
    лиш
    0.07
     Nigerian
    0.07
    _af
    0.06
    arse
    0.06
     život
    0.06
    ै?
    0.06
    ruby
    0.06
    Act Density 0.000%

    No Known Activations