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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols typically used in data or statistics

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

    Numbers near zero

    np_acts-logits-general · gemini-2.0-flash

    statistical phrases or values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    belea
    -0.55
    انيف
    -0.54
    soort
    -0.54
     @"/
    -0.53
    ')):
    -0.53
     aload
    -0.52
    qrstuvwxyz
    -0.52
    "][
    -0.51
     cura
    -0.51
    ===========
    -0.51
    POSITIVE LOGITS
    httphttps
    0.75
    ThroughAttribute
    0.66
    subsubsection
    0.64
    subsection
    0.62
    CloseOperation
    0.61
     őket
    0.61
    cmath
    0.59
    ContentLoaded
    0.59
    MigrationBuilder
    0.57
     AssemblyCompany
    0.57
    Act Density 0.826%

    No Known Activations