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

    Neuronpedia

    INDEX
    Explanations

    policy questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഇമാം
    0.32
     sayesinde
    0.31
     grazie
    0.30
     Malgré
    0.30
     moradores
    0.30
     dzięki
    0.30
     учун
    0.29
     hippocampus
    0.29
     murió
    0.29
    теше
    0.29
    POSITIVE LOGITS
     policy
    0.39
    政策
    0.38
    policy
    0.37
    has
    0.35
    Parliament
    0.35
    questions
    0.34
    n
    0.34
     policies
    0.34
    regulatory
    0.33
    have
    0.33
    Act Density 0.000%

    No Known Activations