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

    Neuronpedia

    INDEX
    Explanations

    deck item build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ابقات
    0.51
    ও
    0.42
    ناط
    0.41
    Shutdown
    0.40
     infrastrukt
    0.40
    infrastructure
    0.40
     شو
    0.38
    قص
    0.38
    짐
    0.38
     পাহ
    0.38
    POSITIVE LOGITS
    ay
    0.44
    共通
    0.43
     combinations
    0.41
    च्चय
    0.41
     selected
    0.41
     duplicate
    0.40
    xcuserdatad
    0.40
    combinations
    0.40
     heed
    0.39
    を作成
    0.39
    Act Density 0.002%

    No Known Activations