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

    Neuronpedia

    INDEX
    Explanations

    mentions of people and their interactions or references throughout the text

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

    people and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifikationen
    -0.46
    authier
    -0.41
    kwür
    -0.41
    rzost
    -0.40
    الدراسه
    -0.40
    ény
    -0.39
    Possui
    -0.38
    stätte
    -0.37
    ografija
    -0.37
    uspiel
    -0.37
    POSITIVE LOGITS
     people
    0.69
    people
    0.69
    everybody
    0.63
    PEOPLE
    0.60
     ludzie
    0.60
     lidí
    0.59
     PEOPLE
    0.59
    somebody
    0.59
    People
    0.59
     folks
    0.58
    Act Density 0.027%

    No Known Activations