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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and monetary amounts

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

    Numerical values following hyphens

    np_acts-logits-general · gemini-2.0-flash

    quantities of posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FetchType
    -0.74
    исленность
    -0.74
    interopRequire
    -0.72
    webElementXpaths
    -0.72
    tvguidetime
    -0.70
    脚注の使い方
    -0.69
    IntoConstraints
    -0.68
    +:+
    -0.67
     '\\;'
    -0.64
    AndEndTag
    -0.64
    POSITIVE LOGITS
     thousands
    0.79
     hundreds
    0.79
     Hundreds
    0.65
     dozens
    0.64
    hundreds
    0.64
    thousands
    0.62
    Thousands
    0.61
    Hundreds
    0.59
     Thousands
    0.58
     ſeveral
    0.57
    Act Density 3.345%

    No Known Activations