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

    Neuronpedia

    INDEX
    Explanations

    783

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    菜
    -0.07
     Україн
    -0.07
    _Menu
    -0.06
    avery
    -0.06
    Repository
    -0.06
     ldc
    -0.06
     thirteen
    -0.06
    xde
    -0.06
     Keywords
    -0.06
    \xb
    -0.06
    POSITIVE LOGITS
     Wes
    0.07
     تق
    0.07
     gag
    0.07
    拥
    0.07
    φυ
    0.06
     Ars
    0.06
    -span
    0.06
    _epsilon
    0.06
     Baron
    0.06
     requirement
    0.06
    Act Density 0.018%

    No Known Activations