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

    Neuronpedia

    INDEX
    Explanations

    political maneuvering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spart
    0.47
    Crim
    0.46
    牖
    0.44
    Cle
    0.43
    opponent
    0.43
    Change
    0.43
    Advance
    0.42
    ्यू
    0.42
     Illinois
    0.42
     ज्वाइन
    0.41
    POSITIVE LOGITS
     bodied
    0.51
     然而
    0.48
     गुरूवार
    0.45
     brewed
    0.45
    ámico
    0.45
    গঠনিক
    0.43
     совмести
    0.43
    ólogos
    0.42
     hành
    0.41
    生的
    0.41
    Act Density 0.001%

    No Known Activations