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

    Neuronpedia

    INDEX
    Explanations

    search and information retrieval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="_
    0.40
     voluntad
    0.38
    -_
    0.38
     vontade
    0.38
     *_
    0.38
     Vanden
    0.38
    呿
    0.37
     supone
    0.37
    燙
    0.37
     "_
    0.36
    POSITIVE LOGITS
    Wikipedia
    0.61
     wikipedia
    0.54
     Wikipedia
    0.52
    Bing
    0.48
    wikipedia
    0.47
     Britannica
    0.44
     Wikip
    0.44
     Vikipedi
    0.43
     Wikipédia
    0.43
    wiki
    0.42
    Act Density 0.001%

    No Known Activations