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

    Neuronpedia

    INDEX
    Explanations

    academic identifiers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mensajes
    0.66
     पिक्च
    0.66
     cramping
    0.64
    ຂໍ້ມ
    0.62
     इनकम
    0.61
     conversaciones
    0.61
     pensamientos
    0.61
     capacidad
    0.60
     setores
    0.59
     enemies
    0.59
    POSITIVE LOGITS
     DOI
    2.22
    DOI
    2.22
    doi
    2.20
     doi
    2.05
     arXiv
    1.71
     PubMed
    1.70
    PubMed
    1.66
    arXiv
    1.60
     journal
    1.52
    Abstract
    1.48
    Act Density 0.145%

    No Known Activations