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

    Neuronpedia

    INDEX
    Explanations

    bilateral cooperation and agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    国内外
    1.07
     indoors
    0.91
     گھر
    0.87
     sadistic
    0.83
     வெளிப்புற
    0.81
     worldly
    0.81
     internal
    0.80
     worldwide
    0.80
     abroad
    0.80
     surround
    0.79
    POSITIVE LOGITS
     bilater
    1.59
     bilateral
    1.57
     Cooperation
    1.53
     mutual
    1.50
     cooperation
    1.50
    Mutual
    1.37
     coopération
    1.36
     Mutual
    1.35
     friendship
    1.30
     reciproc
    1.29
    Act Density 0.105%

    No Known Activations