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

    Neuronpedia

    INDEX
    Explanations

    calculating median

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사람
    0.29
     dette
    0.27
     homers
    0.25
    ...),
    0.25
    ?),
    0.24
    ').':
    0.24
     ইহাতে
    0.24
     idha
    0.23
    ܠܐ
    0.23
     पुअनि
    0.23
    POSITIVE LOGITS
    ↵↵
    0.58
    ↵↵↵
    0.47
    ↵
    0.47
    ↵↵↵↵↵
    0.45
    ↵↵↵↵
    0.44
    ↵↵↵↵↵↵
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.33
              
    0.32
    <start_of_image>
    0.32
    <h2>
    0.31
    Act Density 3.789%

    No Known Activations