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

    Neuronpedia

    INDEX
    Explanations

    CIA government programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Defense
    0.40
     NIG
    0.40
    IGENCE
    0.39
    weisung
    0.39
    Intelligence
    0.38
     informé
    0.37
    خول
    0.36
    нету
    0.36
     distributional
    0.36
    Requirement
    0.36
    POSITIVE LOGITS
     program
    0.45
     CIA
    0.44
    rentices
    0.43
    メン
    0.40
     პროგრამ
    0.40
     অ্য
    0.39
    變
    0.39
     Program
    0.39
     plausible
    0.39
     läk
    0.39
    Act Density 0.002%

    No Known Activations