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

    Neuronpedia

    INDEX
    Explanations

    negations in the text

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

    not only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.50
     esame
    -0.50
    KommentareTeilen
    -0.46
    xml
    -0.45
    EndContext
    -0.44
    xaml
    -0.43
     Verlauf
    -0.43
     xml
    -0.43
     Xml
    -0.42
    XML
    -0.41
    POSITIVE LOGITS
     nahilalakip
    0.61
    IVEREF
    0.54
    owohl
    0.51
    хьтан
    0.50
    不仅
    0.49
    ſelves
    0.46
    InstrumentedTest
    0.46
    だけでなく
    0.45
     nejen
    0.45
    раздо
    0.44
    Act Density 0.015%

    No Known Activations