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

    Neuronpedia

    INDEX
    Explanations

    important questions or requests for information

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

    sentence starters or question introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gyhoeddwyd
    -0.56
    MLLoader
    -0.51
    timewa
    -0.50
    __':
    -0.48
    RegressionTest
    -0.48
    :✨
    -0.47
     IBOutlet
    -0.47
    tldr
    -0.47
    schild
    -0.47
    principalTable
    -0.47
    POSITIVE LOGITS
    sidemargin
    0.45
     území
    0.35
    WriteTagHelper
    0.34
     wikipagina
    0.34
    Activités
    0.34
     børn
    0.33
    ならず
    0.32
     activiteiten
    0.32
    errHandler
    0.32
     Verpflich
    0.32
    Act Density 0.053%

    No Known Activations