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

    Neuronpedia

    INDEX
    Explanations

    personal details and professional backgrounds of individuals

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

    Personal introductions or biographies

    np_acts-logits-general · gemini-2.0-flash

    his/her passions and interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.69
    famous
    -0.58
     berühmten
    -0.58
    ########.
    -0.57
    mişti
    -0.55
     célèbres
    -0.54
     earlier
    -0.54
     eux
    -0.53
     objected
    -0.53
    Exactly
    -0.53
    POSITIVE LOGITS
     enjoys
    0.80
     loves
    0.79
     passions
    0.76
     passionate
    0.76
     disfruta
    0.73
     strives
    0.70
     graag
    0.69
    pires
    0.68
     disfru
    0.68
     currently
    0.67
    Act Density 0.231%

    No Known Activations