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

    Neuronpedia

    INDEX
    Explanations

    various forms of URLs or references to external content

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

    technical documentation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lectric
    -0.44
    itet
    -0.43
    elek
    -0.40
    elect
    -0.38
    ily
    -0.37
     Ing
    -0.37
    lad
    -0.36
    arm
    -0.36
    rad
    -0.35
    tly
    -0.35
    POSITIVE LOGITS
    AndEndTag
    1.09
    RegressionTest
    0.87
    IndentedString
    0.82
     propOrder
    0.81
     snippetHide
    0.81
    parsedMessage
    0.78
    enumi
    0.77
     يتيمه
    0.77
    хьтан
    0.77
    tagHelperRunner
    0.76
    Act Density 0.002%

    No Known Activations