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

    Neuronpedia

    INDEX
    Explanations

    network systems and servers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UL
    0.52
    AIRMAN
    0.52
    EN
    0.50
    ف
    0.49
    KU
    0.46
    binder
    0.43
    jul
    0.43
    HUN
    0.43
    kul
    0.43
    สต
    0.42
    POSITIVE LOGITS
    ၸ
    0.48
     Stephanie
    0.47
     Mosc
    0.46
     тести
    0.46
    ឆ្នាំ
    0.46
     mesures
    0.46
    特定の
    0.46
     gauche
    0.46
     güçlü
    0.46
     સમસ્યા
    0.46
    Act Density 0.002%

    No Known Activations