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

    Neuronpedia

    INDEX
    Explanations

    references to actions or states of being, particularly related to connection and existence

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

    foreign language markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XDECREF
    -0.52
     مشين
    -0.44
     ✭✭
    -0.44
    interopRequire
    -0.43
     referenties
    -0.41
    发表于
    -0.40
    DataAnnotations
    -0.40
     labor
    -0.40
    ことなく
    -0.38
     transcriptional
    -0.38
    POSITIVE LOGITS
     disambiguazione
    0.49
     Económica
    0.47
     Olsson
    0.45
     Eſ
    0.45
     Absch
    0.45
    Absch
    0.44
     Anſ
    0.44
    aarrggbb
    0.44
     cromado
    0.44
    etcode
    0.43
    Act Density 0.095%

    No Known Activations