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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize significance or prominence

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

    most important, notable, principal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.52
    webElementGuid
    -0.47
    SID
    -0.46
    CFD
    -0.42
    UserDetails
    -0.42
     DTM
    -0.42
     shopee
    -0.42
    makeConstraints
    -0.41
     DZ
    -0.41
    ſelves
    -0.41
    POSITIVE LOGITS
     principales
    0.59
     principaux
    0.58
    principal
    0.58
     principal
    0.57
     utama
    0.56
     главное
    0.54
     principais
    0.54
     voran
    0.53
     principali
    0.53
     wichtigste
    0.51
    Act Density 0.044%

    No Known Activations