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

    Neuronpedia

    INDEX
    Explanations

    concepts related to numerical superiority or inferiority in groups

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

    quantity comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.46
    InputTagHelper
    -0.40
    GeneratedValue
    -0.37
    mobileqq
    -0.36
    ⎨
    -0.35
    Fram
    -0.34
    UrlResolution
    -0.34
     FontFamily
    -0.34
    geon
    -0.33
    Revenir
    -0.33
    POSITIVE LOGITS
     outnumbered
    0.66
    TypedDataSet
    0.52
     manpower
    0.52
    numer
    0.52
     Majority
    0.47
     thinned
    0.46
     đông
    0.46
     numerically
    0.45
     minority
    0.45
    DockStyle
    0.45
    Act Density 0.091%

    No Known Activations