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

    Neuronpedia

    INDEX
    Explanations

    words related to leadership or authority

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

    "Lead" followed by certain prepositions

    np_acts-logits-general · gemini-2.0-flash

    lead to or lead-up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.68
    évaluateur
    -0.65
    ieee
    -0.63
    '}';
    -0.63
    googleapis
    -0.58
    CloseOperation
    -0.58
    Rhestr
    -0.57
    kammer
    -0.57
    rativa
    -0.57
    loài
    -0.57
    POSITIVE LOGITS
     astray
    0.97
    Leads
    0.73
    gering
    0.66
     edge
    0.66
    edge
    0.62
     Leads
    0.61
     leads
    0.60
    一步
    0.58
     pack
    0.58
    leads
    0.56
    Act Density 0.072%

    No Known Activations