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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to studies

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

    Numbers followed by commas or decimals

    np_acts-logits-general · gemini-2.0-flash

    numbers and code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.58
     StringTokenizer
    -0.58
    ActionMode
    -0.58
     متعلقه
    -0.57
     iprot
    -0.56
     oprot
    -0.54
    ंदीखरीदारी
    -0.53
    XmlIgnore
    -0.50
    ItemBackground
    -0.49
     mergeFrom
    -0.49
    POSITIVE LOGITS
     mil
    0.62
    SerializedName
    0.56
     mila
    0.55
     invokingState
    0.53
    mila
    0.53
     duiz
    0.51
    findpost
    0.48
    ędzynarod
    0.48
    Javadoc
    0.48
    Milli
    0.46
    Act Density 0.117%

    No Known Activations