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

    Neuronpedia

    INDEX
    Explanations

    Donald Trump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    い
    2.05
    ا
    1.89
    ный
    1.88
    ı
    1.80
    и
    1.80
    ε
    1.80
    ਨ
    1.76
    ен
    1.74
    ਰ
    1.65
    ኩል
    1.63
    POSITIVE LOGITS
    ्रेडिट
    1.93
    gehend
    1.81
    ﻅ
    1.78
    ur
    1.73
    el
    1.70
    o
    1.66
    miller
    1.66
     específicos
    1.65
    is
    1.62
    m
    1.62
    Act Density 0.001%

    No Known Activations