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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships among entities, particularly emphasizing commonalities and communal aspects

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

    our and our

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.96
     فريبيس
    -0.81
    DotNetBar
    -0.75
    <unused74>
    -0.68
    <unused42>
    -0.68
    <unused14>
    -0.68
    <unused8>
    -0.68
    <unused51>
    -0.68
    [@BOS@]
    -0.68
    <pad>
    -0.68
    POSITIVE LOGITS
     indeed
    0.87
     beyond
    0.74
     ultimately
    0.73
    indeed
    0.70
    beyond
    0.58
     ourselves
    0.55
     broader
    0.55
     Indeed
    0.54
    Indeed
    0.53
     everyone
    0.52
    Act Density 0.069%

    No Known Activations