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

    Neuronpedia

    INDEX
    Explanations

    ios app code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rana
    0.43
    knopf
    0.42
    heast
    0.40
     hongos
    0.40
     gele
    0.39
    秾
    0.39
    uskal
    0.38
    swadian
    0.37
    seo
    0.37
     lama
    0.37
    POSITIVE LOGITS
     AppDelegate
    0.81
     UIApplication
    0.75
    AppDelegate
    0.75
    Bundle
    0.72
     UserDefaults
    0.66
     application
    0.64
    Application
    0.64
     Bundle
    0.63
     app
    0.62
     App
    0.62
    Act Density 0.009%

    No Known Activations