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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating explanations or justifications

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

    The following word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pageContext
    -0.66
    featureID
    -0.57
    ArrowToggle
    -0.56
     Италијани
    -0.50
    Хьажоргаш
    -0.50
    AccessorTable
    -0.50
     disambiguazione
    -0.48
    SharedCtor
    -0.48
    rungsseite
    -0.45
     beginnetje
    -0.45
    POSITIVE LOGITS
    enheim
    0.44
    edicated
    0.42
    ftances
    0.41
    ſcher
    0.40
    狙
    0.39
    VYMaps
    0.37
     kasarigan
    0.37
    spesies
    0.36
    rådet
    0.36
    asuring
    0.36
    Act Density 0.024%

    No Known Activations