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

    Neuronpedia

    INDEX
    Explanations

    code-related programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ולנד
    0.83
     Vision
    0.76
    Auction
    0.74
     wszel
    0.74
     તૈયાર
    0.71
    Neither
    0.71
    Both
    0.70
    World
    0.69
    Applying
    0.69
    Applied
    0.69
    POSITIVE LOGITS
     مذکور
    0.81
     workpiece
    0.78
    ,\\
    0.75
    。...
    0.71
    🗒
    0.69
    🤜
    0.69
     해당
    0.68
     ১৯৭
    0.68
     sawdust
    0.67
     அதனை
    0.67
    Act Density 1.813%

    No Known Activations