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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical data analysis and research methodologies

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

    Large numerical quantities

    np_acts-logits-general · gemini-2.0-flash

    quantities of people or things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StringTokenizer
    -0.56
     SafeMath
    -0.55
    msgTypes
    -0.55
    PerformLayout
    -0.53
    jstor
    -0.53
    CodedInputStream
    -0.52
    WriteTagHelper
    -0.52
    GenerationType
    -0.52
    parsedMessage
    -0.51
    adə
    -0.51
    POSITIVE LOGITS
     thousands
    3.22
     hundreds
    3.15
    thousands
    2.83
    hundreds
    2.75
     Thousands
    2.64
    Thousands
    2.62
     Hundreds
    2.56
    Hundreds
    2.51
     tens
    2.51
     millions
    2.43
    Act Density 1.020%

    No Known Activations