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

    Neuronpedia

    INDEX
    Explanations

    names of people and authors

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

    Tokens after Spanish surnames

    np_acts-logits-general · gemini-2.0-flash

    Hispanic names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noires
    -0.79
     Guimarães
    -0.69
     étoit
    -0.64
     avoient
    -0.62
     étoient
    -0.61
     poffible
    -0.60
     auroit
    -0.59
     Jogo
    -0.58
     Mercurio
    -0.58
     Antônio
    -0.56
    POSITIVE LOGITS
     de
    0.81
     del
    0.59
     y
    0.59
     Ort
    0.56
     River
    0.55
     JIM
    0.55
     astore
    0.54
     fern
    0.54
    abspath
    0.54
    Jim
    0.52
    Act Density 0.280%

    No Known Activations