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

    Neuronpedia

    INDEX
    Explanations

    references to race and identity in the context of political discussions

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

    presidents or the White House

    np_acts-logits-general · gemini-2.0-flash

    president and white house

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JpaRepository
    -0.61
    dersfield
    -0.59
     extrinsic
    -0.58
    protoimpl
    -0.58
    脚注の使い方
    -0.54
    Carriera
    -0.53
    Parcel
    -0.53
     متعلقه
    -0.52
     חבר
    -0.52
    lami
    -0.51
    POSITIVE LOGITS
     presidential
    1.32
     Presidential
    1.24
    Presidential
    1.21
     presidencial
    1.10
     President
    1.05
     White
    1.04
     presidency
    0.97
    President
    0.94
     Presidency
    0.94
     president
    0.93
    Act Density 0.314%

    No Known Activations