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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VA
    -0.46
    sih
    -0.45
     cheval
    -0.43
    álni
    -0.43
    ieh
    -0.43
    يا
    -0.41
    šiu
    -0.41
     menthe
    -0.41
    idist
    -0.41
    vav
    -0.41
    POSITIVE LOGITS
    DockStyle
    0.63
     étrangère
    0.61
     @"/
    0.61
    ValueGeneration
    0.60
     defaultstate
    0.60
     asiatique
    0.60
     &___
    0.58
     Now
    0.56
    الإنجليزية
    0.55
    party
    0.54
    Act Density 0.013%

    No Known Activations