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

    Neuronpedia

    INDEX
    Explanations

    doi links and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paradigma
    0.64
     grano
    0.57
     documentos
    0.57
     temat
    0.57
     istilah
    0.55
     regole
    0.55
     dokument
    0.55
     vão
    0.54
     diagrama
    0.54
     diva
    0.54
    POSITIVE LOGITS
    1
    0.75
    doi
    0.74
    J
    0.71
    0
    0.67
     doi
    0.64
    j
    0.63
    DOI
    0.62
     DOI
    0.59
    3
    0.58
    9
    0.58
    Act Density 0.003%

    No Known Activations