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

    Neuronpedia

    INDEX
    Explanations

    references to the article title or headings

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

    Comes after the word "The"

    np_acts-logits-general · gemini-2.0-flash

    the followed by titles or specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sobě
    -0.47
     Touristen
    -0.46
    Хьажоргаш
    -0.45
    -0.44
     lentejuelas
    -0.44
    -------
    -0.43
     pierna
    -0.43
    hubanes
    -0.42
     Bewußt
    -0.42
     manguera
    -0.42
    POSITIVE LOGITS
     ultimate
    0.49
     Pham
    0.47
     Ultimate
    0.47
     Importance
    0.47
     Great
    0.47
     ulti
    0.46
    ultimate
    0.46
     tao
    0.44
    Making
    0.43
     BIG
    0.43
    Act Density 0.146%

    No Known Activations