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

    Neuronpedia

    INDEX
    Explanations

    mentions of positive attributes and sentiments

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

    "a" or "an" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    a descriptive noun or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VIAF
    -0.64
    etheless
    -0.64
     Likely
    -0.61
     getRule
    -0.61
     IndexError
    -0.60
    できれば
    -0.60
    nais
    -0.59
     dandy
    -0.58
     rows
    -0.58
     Bourgoin
    -0.57
    POSITIVE LOGITS
     huge
    0.62
     sense
    0.60
     really
    0.59
     intérêts
    0.57
     culmination
    0.54
     AssemblyCompany
    0.54
     constant
    0.51
    huge
    0.50
     little
    0.50
     sensazione
    0.50
    Act Density 0.149%

    No Known Activations