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

    Neuronpedia

    INDEX
    Explanations

    mentions of treaties and political agreements related to territorial disputes

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

    Follows "a" or "the" and precedes a proper noun

    np_acts-logits-general · gemini-2.0-flash

    international agreements and protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IContainer
    -0.70
     lifecycle
    -0.57
    ValueStyle
    -0.57
     Upstream
    -0.56
    foglal
    -0.55
    τισ
    -0.54
     parten
    -0.53
     गुण
    -0.52
     genders
    -0.52
     Transparency
    -0.52
    POSITIVE LOGITS
     '\\;'
    0.69
     peace
    0.63
     Meksiku
    0.63
     neutral
    0.61
    UTRAL
    0.57
    Peace
    0.56
    WireFormatLite
    0.55
     secret
    0.54
    SQLException
    0.53
    rinol
    0.53
    Act Density 0.824%

    No Known Activations