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

    Neuronpedia

    INDEX
    Explanations

    Senator or Senate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    响
    0.39
     কীট
    0.38
    вяз
    0.38
     성능
    0.37
     หมู่
    0.37
    တွ
    0.37
    zás
    0.37
     HP
    0.37
     साध
    0.36
    Training
    0.36
    POSITIVE LOGITS
     senators
    1.84
     senator
    1.82
     Senator
    1.81
     Senators
    1.78
    Senator
    1.76
     Senate
    1.74
    Senate
    1.69
     senate
    1.62
     senador
    1.55
     sen
    1.50
    Act Density 0.005%

    No Known Activations