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

    Neuronpedia

    INDEX
    Explanations

    HTML and JavaScript code elements

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theoretical
    -0.43
    symmetric
    -0.41
     bonté
    -0.40
    ster
    -0.40
    coin
    -0.39
     symmetrical
    -0.38
     uren
    -0.38
    theoretical
    -0.38
     fourrure
    -0.38
     bezit
    -0.38
    POSITIVE LOGITS
    webElementXpaths
    0.67
     Roskov
    0.62
    хьтан
    0.57
     disambiguazione
    0.54
    DockStyle
    0.51
    Rohy
    0.51
    contentLoaded
    0.50
    rawDesc
    0.49
     Савезне
    0.49
     OMITBAD
    0.48
    Act Density 0.010%

    No Known Activations