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

    Neuronpedia

    INDEX
    Explanations

    references to government actions and policies related to trade restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    policy announcements after pronouncements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RunWith
    -0.29
     mutu
    -0.29
     table
    -0.28
    Par
    -0.28
     compara
    -0.27
    Supported
    -0.26
    Tre
    -0.26
    Bug
    -0.25
     Ist
    -0.24
     vot
    -0.24
    POSITIVE LOGITS
    +#+#
    0.92
     fieldNum
    0.72
     Menſchen
    0.69
    0.67
    liceerd
    0.67
    <unused23>
    0.66
    <unused41>
    0.66
    <unused32>
    0.66
    <pad>
    0.66
    <unused1>
    0.66
    Act Density 0.023%

    No Known Activations