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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships

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

    Follows punctuation marks and indicates conclusions

    np_acts-logits-general · gemini-2.0-flash

    conclude statements; following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PublicKey
    -0.56
    béco
    -0.55
    jspb
    -0.55
     native
    -0.55
    httphttps
    -0.55
    crivez
    -0.55
    Rohy
    -0.51
    tagHelperRunner
    -0.51
    oulders
    -0.51
    latan
    -0.50
    POSITIVE LOGITS
     conclude
    0.75
     CreateTagHelper
    0.73
     concluir
    0.69
     concluye
    0.67
     conclure
    0.67
     conclusion
    0.63
     concludes
    0.63
     concluding
    0.62
     conclusión
    0.61
     conclusão
    0.61
    Act Density 1.154%

    No Known Activations