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

    Neuronpedia

    INDEX
    Explanations

    key details or values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CONCLUSIONS
    0.46
     Processes
    0.44
     procesos
    0.41
    Conclusions
    0.40
     Conclusions
    0.40
     Veranstaltungen
    0.38
    গর্
    0.38
     anál
    0.38
     analý
    0.38
     beserta
    0.37
    POSITIVE LOGITS
     variables
    1.48
     parameters
    1.38
     values
    1.27
    variables
    1.20
    parameters
    1.09
    变量
    1.09
    values
    1.08
     Variables
    1.08
     параметры
    1.08
     variáveis
    1.07
    Act Density 0.065%

    No Known Activations