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

    Neuronpedia

    INDEX
    Explanations

    concepts related to change and variety

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

    novelty, difference, and change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dentaire
    -0.37
    KURZBESCHREIBUNG
    -0.36
     BigNumber
    -0.36
     epidem
    -0.36
     afbeelding
    -0.34
    ForValue
    -0.34
    andReturn
    -0.33
     prijs
    -0.33
     Zustand
    -0.32
     leggen
    -0.32
    POSITIVE LOGITS
     novelty
    0.72
     innovate
    0.62
     alternatives
    0.62
     alternative
    0.61
     Novelty
    0.60
    alternatives
    0.59
     الرياضيه
    0.59
     freshen
    0.58
     ALTERN
    0.56
    alternative
    0.56
    Act Density 0.009%

    No Known Activations