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

    Neuronpedia

    INDEX
    Explanations

    references to Russia and its associated terms

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

    Russia scandal, investigation, collusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gilman
    -0.51
    Mait
    -0.50
     Highlight
    -0.49
    findpost
    -0.49
     AIM
    -0.49
     Mait
    -0.48
     Gim
    -0.48
     Pla
    -0.47
    PRET
    -0.46
     Wim
    -0.46
    POSITIVE LOGITS
     Russia
    1.04
     Russie
    1.03
    Russia
    0.99
     Russland
    0.85
     Russian
    0.83
     russia
    0.83
     Russians
    0.82
     russes
    0.82
     Rusia
    0.82
    russia
    0.81
    Act Density 0.007%

    No Known Activations