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

    Neuronpedia

    INDEX
    Explanations

    otherwise, historically, understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geometries
    0.46
     Generator
    0.45
     Montreal
    0.45
     yaml
    0.45
     Scheme
    0.44
     scheme
    0.44
     Generation
    0.43
     Separ
    0.43
    configurations
    0.43
    scheme
    0.43
    POSITIVE LOGITS
    ată
    0.43
     adultos
    0.43
    違
    0.43
     vigorous
    0.42
    embrie
    0.42
    тя
    0.42
    無需
    0.42
    시다
    0.41
     votos
    0.41
     sí
    0.40
    Act Density 0.000%

    No Known Activations