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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their mathematical relationships

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

    Numerical values between 0 and 9

    np_acts-logits-general · gemini-2.0-flash

    numbers separated by periods or commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.64
     Lint
    -0.51
    醐
    -0.51
     réfléchir
    -0.49
     pisau
    -0.48
     Panel
    -0.47
    ascin
    -0.47
     hear
    -0.47
    wyżs
    -0.46
     prefent
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.76
    Tikang
    0.70
     quarter
    0.66
    NameInMap
    0.63
     kasarigan
    0.57
    UnsafeEnabled
    0.55
    WebServlet
    0.55
     getItemId
    0.54
    はじめに
    0.54
     BorderRadius
    0.53
    Act Density 0.555%

    No Known Activations