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

    Neuronpedia

    INDEX
    Explanations

    Setting up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    antly
    0.86
    ভিক্ষ
    0.84
    ancji
    0.81
    arding
    0.80
    ިން
    0.80
    HandleTypeDef
    0.79
     socially
    0.77
    >−</
    0.77
    ìm
    0.76
    नोट
    0.75
    POSITIVE LOGITS
     aside
    1.38
    ters
    1.07
    ContentView
    1.03
    FOOT
    1.02
    aside
    1.02
    िंग्स
    1.01
     ulang
    1.01
     νέ
    0.99
    abá
    0.96
    EventListeners
    0.94
    Act Density 0.219%

    No Known Activations