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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or metrics within text

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

    user input marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.60
     CanadaChoose
    -0.50
    SharedDtor
    -0.49
     OMITBAD
    -0.48
     autorytatywna
    -0.47
    SharedCtor
    -0.46
    PreferredItem
    -0.46
    Havolalar
    -0.46
    Биография
    -0.45
     yym
    -0.45
    POSITIVE LOGITS
    素
    0.36
    atural
    0.33
    請繼續往下閱讀
    0.33
    viertel
    0.33
    rungsseite
    0.33
    })`
    0.33
    );"
    0.33
    Hapana
    0.33
    uie
    0.32
     βά
    0.32
    Act Density 0.000%

    No Known Activations