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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _invoke
    -0.08
    
    -0.08
    旗舰
    -0.07
    تحرك
    -0.07
     skill
    -0.07
     addressed
    -0.06
    小龙
    -0.06
    $k
    -0.06
    쁄
    -0.06
     Silent
    -0.06
    POSITIVE LOGITS
    opol
    0.07
     Ukr
    0.07
     всег
    0.07
     często
    0.07
    中级
    0.07
     metals
    0.07
    名校
    0.07
    🔉
    0.06
    egen
    0.06
    .MouseEventHandler
    0.06
    Act Density 0.031%

    No Known Activations