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

    Neuronpedia

    INDEX
    Explanations

    terms related to structured summaries and data analysis

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

    section headings or titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    -0.36
     And
    -0.33
    <eos>
    -0.32
    Referenties
    -0.32
     surrounding
    -0.31
     and
    -0.30
    Мои
    -0.30
     borders
    -0.29
     Nova
    -0.29
     locations
    -0.29
    POSITIVE LOGITS
     disambiguazione
    0.87
    مصادر
    0.68
    parsedMessage
    0.66
     EClass
    0.64
     lenker
    0.62
     ujednoznacz
    0.61
     Италијани
    0.59
     Administrativna
    0.59
    Personendaten
    0.58
     betweenstory
    0.58
    Act Density 0.152%

    No Known Activations