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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical measures related to research studies

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

    Percentages related to counts or proportions

    np_acts-logits-general · gemini-2.0-flash

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.71
    ArgsConstructor
    -0.70
     jutaan
    -0.65
    RegressionTest
    -0.64
    RuleContext
    -0.63
     milliers
    -0.63
    OrBuilder
    -0.62
    Millions
    -0.62
    UpdateCommand
    -0.61
    InputBorder
    -0.59
    POSITIVE LOGITS
     instances
    0.70
     cases
    0.68
     fewer
    0.66
     individuals
    0.65
     eleven
    0.64
     pairs
    0.63
    4
    0.60
     thirteen
    0.60
     counted
    0.60
    6
    0.59
    Act Density 0.922%

    No Known Activations