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

    Neuronpedia

    INDEX
    Explanations

    JFK and Kennedy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ся
    2.25
    ول
    2.02
    いた
    2.02
    ছেন
    1.98
    0
    1.90
    ة
    1.90
    عة
    1.89
    り
    1.82
    ructured
    1.81
     offshoring
    1.80
    POSITIVE LOGITS
    ic
    2.73
    ی
    2.27
    <0x8D>
    2.25
    n
    2.23
    <0x81>
    2.17
    <0x95>
    2.17
    ﻅ
    2.09
    e
    1.91
    <0x98>
    1.81
    offic
    1.79
    Act Density 0.014%

    No Known Activations