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

    Neuronpedia

    INDEX
    Explanations

    references to specific quantities or measurements in a text

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

    the followed by technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upcoming
    -0.46
     AssemblyCompany
    -0.43
    penup
    -0.41
    WriteLiteral
    -0.41
     news
    -0.41
    mybatisplus
    -0.40
    جوايز
    -0.39
    แผน
    -0.38
    󠁢
    -0.38
     diss
    -0.38
    POSITIVE LOGITS
    exitRule
    0.55
     wireType
    0.52
     disambiguazione
    0.48
     PagesJaunes
    0.47
    unzel
    0.47
    Turkish
    0.46
     صفحۀ
    0.45
     člověk
    0.45
    assertThat
    0.45
    ypsies
    0.44
    Act Density 0.293%

    No Known Activations