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

    Neuronpedia

    INDEX
    Explanations

    Trump era and attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.03
    س
    0.92
    า
    0.86
    то
    0.83
    ки
    0.82
    ло
    0.80
    ли
    0.79
    𝘸
    0.79
    ку
    0.77
    ف
    0.77
    POSITIVE LOGITS
     Trump
    1.09
    Trump
    0.93
     I
    0.86
    特朗普
    0.69
    ente
    0.66
    ’
    0.65
     leve
    0.61
     don
    0.59
     trump
    0.54
    entie
    0.54
    Act Density 0.001%

    No Known Activations