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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to demographic or societal issues

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

    Percentages and numerical proportions

    np_acts-logits-general · gemini-2.0-flash

    percentage or count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.84
     AssemblyCulture
    -0.60
     للمعارف
    -0.52
     Savior
    -0.52
    ArgsConstructor
    -0.51
    原始内容存档于
    -0.50
    ="#"><
    -0.50
    Manager
    -0.49
    躇
    -0.48
    ValueStyle
    -0.48
    POSITIVE LOGITS
     out
    0.78
     every
    0.57
     proporción
    0.57
    LayoutConstraint
    0.56
     Every
    0.56
     unknownFields
    0.55
    FormTagHelper
    0.53
    EndContext
    0.52
     estekak
    0.52
    Every
    0.52
    Act Density 0.238%

    No Known Activations