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

    Neuronpedia

    INDEX
    Explanations

    system means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terrorism
    0.42
     carvings
    0.42
     handheld
    0.41
     extradition
    0.39
    颶
    0.39
     терро
    0.39
     Terrorism
    0.38
    रा
    0.38
     Eliz
    0.38
     undersea
    0.37
    POSITIVE LOGITS
    系统的
    0.43
     berarti
    0.41
    unknown
    0.41
    ardon
    0.41
     systèmes
    0.41
    系統
    0.41
    system
    0.40
    systems
    0.40
    浠
    0.39
     Means
    0.39
    Act Density 0.003%

    No Known Activations