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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improvement or enhancement

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

    adjective followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Svensson
    -0.37
     merve
    -0.34
     Lindgren
    -0.34
     nærm
    -0.33
     pères
    -0.33
    balleur
    -0.33
     Ganzen
    -0.33
     africains
    -0.33
     circonstances
    -0.32
     Jungen
    -0.32
    POSITIVE LOGITS
     resourceCulture
    0.79
    AndEndTag
    0.68
    contentLoaded
    0.65
    ########.
    0.65
    <unused51>
    0.64
    <unused23>
    0.64
    <unused14>
    0.64
    <unused41>
    0.64
    <unused8>
    0.64
    [@BOS@]
    0.64
    Act Density 0.024%

    No Known Activations