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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting elements that signify structure in text

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

    place names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.62
    ftagPool
    -0.45
    Personendaten
    -0.43
    yadh
    -0.42
    OGND
    -0.42
    ODB
    -0.41
     <=",
    -0.40
    asas
    -0.40
    ۣ
    -0.40
     Aviv
    -0.37
    POSITIVE LOGITS
    wieś
    0.65
    PreferredItem
    0.59
    RegressionTest
    0.58
     Rural
    0.56
    Referanser
    0.56
     County
    0.54
     rural
    0.53
     Gazetteer
    0.50
    setObjectName
    0.50
     Farmers
    0.49
    Act Density 0.003%

    No Known Activations