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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to statistical analysis methods and techniques

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

    Bonferroni method

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron mainly signals the start of a text segment or the beginning-of-sequence token.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ATIV
    -0.32
     //
    -0.30
    speaking
    -0.27
     Writing
    -0.26
     非
    -0.25
    ↵
    -0.25
    //
    -0.25
     अनुसार
    -0.25
     Your
    -0.24
     Report
    -0.24
    POSITIVE LOGITS
    RenderAtEndOf
    0.83
    ConstraintMaker
    0.79
    WriteTagHelper
    0.78
    0.77
     للاسماء
    0.73
     Geſch
    0.72
     typelib
    0.72
    InputBorder
    0.69
     BoxFit
    0.69
    bootstrapcdn
    0.68
    Act Density 16.102%

    No Known Activations