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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "and" used in various contexts

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

    pairs of names or professional roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.63
    featureID
    -0.62
    -0.62
     onAnimation
    -0.62
    存于互联网档案馆
    -0.62
    principalColumn
    -0.56
    ReusableCell
    -0.55
     HttpNotFound
    -0.54
    AISSEE
    -0.52
    parsedMessage
    -0.52
    POSITIVE LOGITS
     assistants
    0.48
     duo
    0.44
     professors
    0.43
     partners
    0.42
     officers
    0.41
     colleagues
    0.41
     journalists
    0.39
     Drs
    0.39
     collaborators
    0.39
     politicians
    0.38
    Act Density 0.075%

    No Known Activations