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

    Neuronpedia

    INDEX
    Explanations

    references to places and legal or historical context

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

    Follows colons, periods, or prepositions

    np_acts-logits-general · gemini-2.0-flash

    geographic locations and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jérusalem
    -0.89
     Cæsar
    -0.86
     Lithuan
    -0.84
     Moscú
    -0.84
     Giappone
    -0.81
     propOrder
    -0.78
     Turquie
    -0.78
     Dänemark
    -0.77
     Shakspeare
    -0.76
     Venise
    -0.75
    POSITIVE LOGITS
    chó
    0.60
     utafiti
    0.59
    )>>
    0.56
    NUMX
    0.55
    dialement
    0.55
    $'
    0.55
    $',
    0.54
    )';
    0.54
    UTERS
    0.53
    Più
    0.53
    Act Density 0.030%

    No Known Activations