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

    Neuronpedia

    INDEX
    Explanations

    citing sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dayspecial
    0.42
    énagement
    0.42
     пон
    0.41
    Despatx
    0.40
    FunctionName
    0.40
    Optionals
    0.38
     episodios
    0.38
     pon
    0.38
     manio
    0.38
    simulate
    0.37
    POSITIVE LOGITS
     sources
    2.47
    sources
    2.23
     Sources
    2.23
    Sources
    2.13
     source
    2.06
     SOURCES
    2.05
     источники
    2.03
     источников
    2.00
     fuentes
    1.98
    SOURCES
    1.88
    Act Density 0.018%

    No Known Activations