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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connective phrases in a document

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

    connecting different ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.61
    featureID
    -0.61
    uxxxx
    -0.60
     resourceCulture
    -0.57
     ویکی‌پدی
    -0.56
     beginnetje
    -0.56
     мәгълү
    -0.55
    انتهای
    -0.53
    Notae
    -0.51
    -```
    -0.49
    POSITIVE LOGITS
     relish
    0.40
    accumulate
    0.38
    masalahan
    0.38
    while
    0.38
     Utilizamos
    0.37
     člověk
    0.37
     person
    0.36
    々と
    0.36
    person
    0.36
    separate
    0.36
    Act Density 0.013%

    No Known Activations