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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connecting phrases within the text

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

    after conjunctions "or" and "and"

    np_acts-logits-general · gemini-2.0-flash

    enumerating options or descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étoient
    -0.29
     Cliquez
    -0.27
     Keuangan
    -0.27
     uniformes
    -0.26
     někter
    -0.25
    Personendaten
    -0.23
     AudioClip
    -0.23
     avoient
    -0.22
     befolk
    -0.22
     flyg
    -0.21
    POSITIVE LOGITS
     Normdatei
    0.78
    IsMutable
    0.75
     otomatig
    0.73
     مرئيه
    0.71
     चीज़ों
    0.70
    __*/
    0.69
    JspWriter
    0.69
    पया
    0.69
    jooq
    0.68
    IntoConstraints
    0.68
    Act Density 0.546%

    No Known Activations