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

    Neuronpedia

    INDEX
    Explanations

    sections of text related to personal background and career achievements

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

    early life and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     koning
    -0.32
     ra
    -0.29
    Geografi
    -0.29
    自分も
    -0.28
    humans
    -0.27
    users
    -0.27
     yourselves
    -0.27
    fruta
    -0.26
    artists
    -0.26
    下次
    -0.26
    POSITIVE LOGITS
     career
    0.97
     childhood
    0.91
     early
    0.82
     accomplishments
    0.81
    Early
    0.81
     Early
    0.79
     Career
    0.75
     upbringing
    0.75
     EARLY
    0.74
    career
    0.73
    Act Density 0.018%

    No Known Activations