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

    Neuronpedia

    INDEX
    Explanations

    significant historical figures and their contributions to culture or society

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

    Comes after a verb

    np_acts-logits-general · gemini-2.0-flash

    gives context for a president

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paul
    -0.57
     Richard
    -0.57
     Steve
    -0.57
     Michael
    -0.57
     Andrew
    -0.56
     Patrick
    -0.55
     Eric
    -0.55
     Stephen
    -0.54
     Mrs
    -0.54
     David
    -0.54
    POSITIVE LOGITS
     Civil
    0.38
     Human
    0.38
    قایناقلار
    0.37
     Earth
    0.37
     Seventh
    0.37
     utafitiHapana
    0.36
     Downtown
    0.36
     Super
    0.36
     Local
    0.36
    abatic
    0.35
    Act Density 1.750%

    No Known Activations