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

    Neuronpedia

    INDEX
    Explanations

    code structure and programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خلاص
    0.39
     ہاکی
    0.38
     අව
    0.38
    Workbench
    0.36
    วง
    0.36
     اي
    0.36
    arial
    0.36
    ก็จะ
    0.36
     آواز
    0.35
    Aik
    0.35
    POSITIVE LOGITS
     naturelle
    0.39
     migliore
    0.39
     Natur
    0.39
    qu
    0.37
     STILL
    0.37
    ffekt
    0.37
     tileSize
    0.37
     Vogt
    0.37
     mejor
    0.36
     Fonds
    0.36
    Act Density 0.293%

    No Known Activations