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

    Neuronpedia

    INDEX
    Explanations

    the presence of verbs indicating actions or states within the document

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

    "are," "is," "was," or "were" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    describing existing states or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ENTH
    -0.51
     Conſ
    -0.48
    ENN
    -0.47
    tua
    -0.46
    ktır
    -0.46
    espan
    -0.46
     Access
    -0.45
    quial
    -0.44
     Origin
    -0.44
    ποι
    -0.44
    POSITIVE LOGITS
     disponibilités
    0.94
     disambiguazione
    0.76
    <bos>
    0.70
     فريبيس
    0.68
     ModelExpression
    0.66
     مرئيه
    0.65
    0.64
     exist
    0.64
    NewUrlParser
    0.60
     Exists
    0.60
    Act Density 0.660%

    No Known Activations