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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical relations and events involving Russia

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

    White House and NATO diplomacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mountain
    -0.38
    tvguidetime
    -0.38
     Ante
    -0.37
    Instrucciones
    -0.37
    вайтесь
    -0.36
     tính
    -0.36
     Brown
    -0.36
     Rabbit
    -0.35
     Snow
    -0.35
     frowned
    -0.35
    POSITIVE LOGITS
     Majefty
    0.53
    Tembelea
    0.48
     purpoſe
    0.48
    aarrggbb
    0.48
     juſ
    0.48
    libatkan
    0.48
    mtrl
    0.47
     Monfieur
    0.47
     ſta
    0.47
     ſch
    0.46
    Act Density 0.083%

    No Known Activations