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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governance and the qualities necessary for leadership

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

    "of" followed by a country or state

    np_acts-logits-general · gemini-2.0-flash

    prepositional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Referencie
    -0.67
    ביוגרפיה
    -0.59
     clés
    -0.58
     básicamente
    -0.58
     Importantly
    -0.57
    InOrder
    -0.57
     niveaux
    -0.57
    QtWidgets
    -0.57
    нгредіє
    -0.57
     proactively
    -0.55
    POSITIVE LOGITS
     such
    0.75
     eenige
    0.65
     zijne
    0.62
    ValueGeneration
    0.59
     petto
    0.58
    such
    0.57
     eenig
    0.57
     bis
    0.54
     eût
    0.53
     irgend
    0.53
    Act Density 0.620%

    No Known Activations