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

    Neuronpedia

    INDEX
    Explanations

    information that is or becomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adultos
    0.77
     expresó
    0.77
     প্রবৃত্ত
    0.76
     quiere
    0.73
     জানার
    0.73
    uttosto
    0.72
     textos
    0.71
    urbation
    0.69
     llenar
    0.68
     debemos
    0.68
    POSITIVE LOGITS
    खा
    0.73
    ങ്കി
    0.73
    ΰ
    0.67
    Lol
    0.66
     fonbet
    0.66
     ন
    0.64
     లు
    0.64
     sequins
    0.64
    нала
    0.64
    侍
    0.64
    Act Density 0.000%

    No Known Activations