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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating social interactions or personal connections

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

    French, Portuguese, or Spanish words

    np_acts-logits-general · gemini-2.0-flash

    age and expertise terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     děti
    -0.60
     женские
    -0.59
    出版年
    -0.59
     çocuklar
    -0.58
    remel
    -0.58
     himſelf
    -0.56
     Jurí
    -0.56
    zarchiwizowane
    -0.55
     ibunya
    -0.55
     aliados
    -0.55
    POSITIVE LOGITS
     young
    0.60
     expatri
    0.57
    senior
    0.56
    superuser
    0.56
    young
    0.54
     senior
    0.53
    expert
    0.52
     adolescent
    0.52
     sympath
    0.51
    specialist
    0.51
    Act Density 0.044%

    No Known Activations