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

    Neuronpedia

    INDEX
    Explanations

    references to discussions and opinions about societal and personal values

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

    Followed by capitalized names or pronouns

    np_acts-logits-general · gemini-2.0-flash

    Proper nouns and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.51
    <s>
    -0.48
     "..\..\..\
    -0.47
    SharedCtor
    -0.46
     "..\..\
    -0.45
     kli
    -0.44
    عه
    -0.44
     étoit
    -0.44
     crí
    -0.43
    \[
    -0.43
    POSITIVE LOGITS
    ftagPool
    0.89
     defaultstate
    0.85
    Répondre
    0.80
    ритори
    0.77
    LikeLike
    0.70
     Pingback
    0.69
    LikeLiked
    0.67
    Antworten
    0.65
    Fordítás
    0.64
    SpringBootTest
    0.61
    Act Density 0.064%

    No Known Activations