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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters in code or text

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

    section/appendix/im/lemma/cor references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monasterio
    -0.36
     now
    -0.30
    ParallelGroup
    -0.30
     ролях
    -0.29
    ServletRequest
    -0.28
     organes
    -0.28
     humaines
    -0.27
     órganos
    -0.26
     Partager
    -0.26
     hechos
    -0.25
    POSITIVE LOGITS
    Билгалдахарш
    0.77
     незавершена
    0.73
    msgTypes
    0.70
    smithy
    0.69
    Autoritní
    0.69
    󠁣
    0.69
    rawDesc
    0.68
    Vidite
    0.68
    хьтан
    0.67
    OGND
    0.67
    Act Density 0.001%

    No Known Activations