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

    Neuronpedia

    INDEX
    Explanations

    geographic names or place-related terms

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

    country names and demonyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rhestr
    -0.54
    boucles
    -0.48
    expandindo
    -0.48
    ismatic
    -0.47
     faltan
    -0.46
    Referencoj
    -0.46
    catalytic
    -0.46
     lámina
    -0.45
     gustado
    -0.45
    tvguidetime
    -0.45
    POSITIVE LOGITS
     France
    0.76
     Russia
    0.73
     Japan
    0.72
     Germany
    0.72
     China
    0.72
     India
    0.69
     Mexico
    0.68
     Italy
    0.67
    Russia
    0.66
     Europe
    0.63
    Act Density 0.021%

    No Known Activations