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

    Neuronpedia

    INDEX
    Explanations

    references to governmental entities or domains related to government websites

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

    government urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kirsch
    -0.57
    Milan
    -0.52
    Charlotte
    -0.51
    arote
    -0.49
    pearl
    -0.49
     Charlotte
    -0.48
    土耳其
    -0.48
    rack
    -0.48
     Pearce
    -0.48
    くちゃ
    -0.47
    POSITIVE LOGITS
    gov
    1.20
     Gov
    1.01
     gov
    0.99
    Gov
    0.97
    GOV
    0.92
     GOV
    0.91
     government
    0.80
    Gover
    0.74
     gover
    0.72
     Gover
    0.72
    Act Density 0.002%

    No Known Activations