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

    Neuronpedia

    INDEX
    Explanations

    terms associated with controversy and significant decision-making events

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

    controversial situations or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gł
    -0.32
     floating
    -0.30
     chúng
    -0.29
     simple
    -0.28
     représent
    -0.28
     comparison
    -0.26
     gili
    -0.26
     payment
    -0.26
     common
    -0.26
     feeling
    -0.26
    POSITIVE LOGITS
    MessageTagHelper
    0.69
    BufferException
    0.66
    featureID
    0.66
    haikusbot
    0.63
     disambiguazione
    0.62
     informée
    0.62
    tagHelper
    0.60
     iParam
    0.59
    RegistryLite
    0.59
    OGND
    0.59
    Act Density 0.030%

    No Known Activations