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

    Neuronpedia

    INDEX
    Explanations

    titles and ranks related to political leadership

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

    Majority and Minority Leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.36
    pulumi
    -0.36
     él
    -0.31
     research
    -0.31
    含
    -0.30
    WithEmail
    -0.30
    ISC
    -0.30
     password
    -0.29
     <<<<<<<<<<<<<<
    -0.28
    ThroughAttribute
    -0.28
    POSITIVE LOGITS
     Majority
    0.88
    Majority
    0.78
     Leader
    0.73
    Leader
    0.65
     MainAxisSize
    0.64
    majority
    0.62
     LEADER
    0.56
    ConstraintMaker
    0.56
    SerializedSize
    0.55
    sizeCache
    0.55
    Act Density 0.003%

    No Known Activations