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

    Neuronpedia

    INDEX
    Explanations

    terms related to key points and their characteristics in a context of data extraction or feature mapping

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

    key points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.55
    WindowConstants
    -0.52
    出版年
    -0.51
     onPostExecute
    -0.51
    UnitTesting
    -0.48
    ServletException
    -0.46
     poveznice
    -0.45
     &___
    -0.44
     Walkover
    -0.43
    Distribuzione
    -0.43
    POSITIVE LOGITS
     key
    0.75
     Key
    0.74
    Key
    0.71
     KEY
    0.70
    key
    0.68
     Keyes
    0.68
     getKey
    0.64
     Keys
    0.62
    getKey
    0.61
     keys
    0.57
    Act Density 0.012%

    No Known Activations