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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the character '(' in expressions

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

    opening parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.71
    parsedMessage
    -0.69
    featureID
    -0.69
    setVerticalGroup
    -0.67
    tagHelperRunner
    -0.63
    AnimationsModule
    -0.62
    ApiModelProperty
    -0.60
    下载附件
    -0.59
    AccessorTable
    -0.57
    SequentialGroup
    -0.56
    POSITIVE LOGITS
    (
    0.77
     (
    0.60
     a
    0.58
    (\
    0.57
     an
    0.56
    〔
    0.54
     Christian
    0.51
    　　(
    0.51
     [
    0.50
    [
    0.50
    Act Density 0.004%

    No Known Activations