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

    Neuronpedia

    INDEX
    Explanations

    optional parameters or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iyasi
    0.48
    ዎቹ
    0.42
    ческий
    0.41
    ਦ
    0.40
    ুদ
    0.39
    શ
    0.39
    𝚜
    0.39
     പ്രസി
    0.38
    acoes
    0.38
     ficaram
    0.38
    POSITIVE LOGITS
     typical
    0.40
     radiology
    0.40
     Crohn
    0.39
     shimmering
    0.39
     indulging
    0.38
     क्षमता
    0.38
     influenza
    0.38
     mRNA
    0.38
     variability
    0.37
     malnutrition
    0.37
    Act Density 0.001%

    No Known Activations