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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and apostrophes

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

    code and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.93
    StoryboardSegue
    -0.80
    rungsseite
    -0.79
    ImageContext
    -0.77
    DockStyle
    -0.74
     виправивши
    -0.73
     surla
    -0.73
     doInBackground
    -0.72
    帖最后由
    -0.71
    providedIn
    -0.70
    POSITIVE LOGITS
     Saxons
    0.59
     himo
    0.59
     nė
    0.58
     dandy
    0.57
     Goed
    0.55
    ">@
    0.52
    andy
    0.51
     distress
    0.50
    Wut
    0.50
    Podob
    0.50
    Act Density 0.004%

    No Known Activations