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

    Neuronpedia

    INDEX
    Explanations

    Armstrong

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '{
    -0.07
     FRA
    -0.07
     implications
    -0.07
     Rot
    -0.06
     Enterprises
    -0.06
     independents
    -0.06
          
    -0.06
    éri
    -0.06
     Chow
    -0.06
     manufacturers
    -0.06
    POSITIVE LOGITS
     доз
    0.07
    kits
    0.07
     jednání
    0.07
     Panda
    0.07
    밍
    0.07
    áv
    0.06
     전용면적
    0.06
     Bağ
    0.06
     indoors
    0.06
    -url
    0.06
    Act Density 0.043%

    No Known Activations