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

    Neuronpedia

    INDEX
    Explanations

    elements related to characteristics of leadership and perception in authority figures

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

    "The" followed by a title or descriptor

    np_acts-logits-general · gemini-2.0-flash

    prominent figures and leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saites
    -0.52
     initComponents
    -0.51
    vábbi
    -0.50
    Indented
    -0.47
     humid
    -0.46
    URIComponent
    -0.46
    RefNanny
    -0.46
    CodeAttribute
    -0.45
     चीज़ों
    -0.45
     extensive
    -0.45
    POSITIVE LOGITS
     leader
    0.87
     hero
    0.87
     savior
    0.82
     ambassador
    0.75
     king
    0.73
     champion
    0.73
    ScopeManager
    0.73
    somebody
    0.72
    leader
    0.72
     spokesperson
    0.71
    Act Density 0.405%

    No Known Activations