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

    Neuronpedia

    INDEX
    Explanations

    publication identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defensive
    0.46
     boobs
    0.41
     faq
    0.41
     blouses
    0.41
     announcements
    0.40
     warships
    0.40
     reservar
    0.40
    ുവരി
    0.39
    分別
    0.39
    ोटोरोला
    0.39
    POSITIVE LOGITS
     doi
    1.30
    doi
    1.24
    DOI
    1.22
     DOI
    1.20
     Doi
    0.98
     PMID
    0.81
    ISSN
    0.73
     ISSN
    0.69
     JSTOR
    0.64
    dx
    0.60
    Act Density 0.005%

    No Known Activations