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

    Neuronpedia

    INDEX
    Explanations

    hashtags and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مر
    0.82
    腖
    0.79
     Citi
    0.76
     Tesla
    0.72
     Exceptions
    0.72
     Displays
    0.72
    ប្ប
    0.71
     Publication
    0.71
     commenter
    0.70
     Sait
    0.70
    POSITIVE LOGITS
    Tag
    1.73
    Tags
    1.70
     tag
    1.68
     tags
    1.66
    tags
    1.56
     Tag
    1.52
    タグ
    1.49
     Tags
    1.49
     hashtags
    1.47
    Keywords
    1.45
    Act Density 0.108%

    No Known Activations