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

    Neuronpedia

    INDEX
    Explanations

    references to versions and editions in documents

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

    issue, episode, release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‍
    -0.41
    Украина
    -0.40
     Euph
    -0.38
    Ἁ
    -0.38
     paul
    -0.37
     Polit
    -0.36
     Украї
    -0.36
     protoimpl
    -0.36
    Brus
    -0.35
     Profession
    -0.35
    POSITIVE LOGITS
     of
    0.93
     ofthe
    0.81
    ของ
    0.65
    ofthe
    0.64
     của
    0.64
     della
    0.53
     kasarigan
    0.53
    XmlAccessType
    0.52
     της
    0.50
    OfThe
    0.48
    Act Density 0.197%

    No Known Activations