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

    Neuronpedia

    INDEX
    Explanations

    numerical data, particularly values associated with statistical measurements

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

    Hexadecimal representations starting with "0x0"

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers in code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.68
    fillType
    -0.66
    ukone
    -0.66
    URLException
    -0.66
    MockBean
    -0.65
    
    -0.65
    MessageTagHelper
    -0.64
     FishBase
    -0.64
    bufio
    -0.63
    styleType
    -0.63
    POSITIVE LOGITS
    0
    0.75
    ypeł
    0.49
    ########.
    0.47
    ittäin
    0.46
    cookieParser
    0.46
    aska
    0.45
     scoreless
    0.44
    IRM
    0.44
    mable
    0.42
    ยว
    0.42
    Act Density 0.684%

    No Known Activations