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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.43
    paravant
    -0.40
    RegressionTest
    -0.39
    luia
    -0.38
    guila
    -0.37
    IANGLES
    -0.36
     τά
    -0.36
    égard
    -0.35
     plainte
    -0.35
     internas
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.64
    oredCriteria
    0.61
     ujednoznacz
    0.61
     怎样
    0.53
    存于互联网档案馆
    0.51
    awtextra
    0.49
     שוליים
    0.47
     referrerpolicy
    0.47
    неопр
    0.47
    sizeCache
    0.46
    Act Density 0.000%

    No Known Activations