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

    Neuronpedia

    INDEX
    Explanations

    action verbs that typically initiate operations or commands

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

    generating code or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.50
     oprot
    -0.46
    StructEnd
    -0.44
     jLabel
    -0.43
    webElementXpaths
    -0.42
    MessageTagHelper
    -0.40
     дописавши
    -0.39
     <=",
    -0.38
     EClass
    -0.37
    TagMode
    -0.36
    POSITIVE LOGITS
    0.52
    cic
    0.51
     cic
    0.47
    Dib
    0.46
    Flex
    0.46
     conjure
    0.46
    AddHtmlAttribute
    0.45
    Cic
    0.45
    IContainer
    0.45
    esign
    0.44
    Act Density 0.011%

    No Known Activations