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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the concept of "addition" or "increased amounts."

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

    in addition to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     énergé
    -0.54
    LEGGI
    -0.54
    expandindo
    -0.50
    UnusedPrivate
    -0.47
    cartão
    -0.46
    SequentialGroup
    -0.44
    abestanden
    -0.44
     underworld
    -0.43
    getJSONObject
    -0.43
    richTextPanel
    -0.42
    POSITIVE LOGITS
     selain
    0.75
    Besides
    0.68
    besides
    0.68
     besides
    0.65
     naast
    0.65
     oltre
    0.61
    Alongside
    0.60
    мимо
    0.59
    Including
    0.59
    他に
    0.57
    Act Density 0.017%

    No Known Activations