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

    Neuronpedia

    INDEX
    Explanations

    various forms of reasoning and consideration in argumentation

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

    Beginning of a summary or conclusion

    np_acts-logits-general · gemini-2.0-flash

    these reasons or considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.71
    GEBURTSDATUM
    -0.70
    :✨
    -0.62
     CreateTagHelper
    -0.60
     Administrativna
    -0.59
     noDo
    -0.59
    principalColumn
    -0.57
    sizeCache
    -0.57
    majánló
    -0.56
     صوتيه
    -0.56
    POSITIVE LOGITS
    Enllaces
    0.37
     foregoing
    0.36
     ویکی‌پدیای
    0.32
    mapreduce
    0.31
     these
    0.31
     above
    0.30
     fenti
    0.28
     Mr
    0.27
     clues
    0.27
     but
    0.27
    Act Density 0.460%

    No Known Activations