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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific structural elements within a text

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

    housing features and property details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kuning
    -0.43
    toMatchSnapshot
    -0.43
     怎样
    -0.42
     Horowitz
    -0.42
     porcentual
    -0.41
     plausible
    -0.41
     Svensson
    -0.40
    rawValue
    -0.40
     Levinson
    -0.40
     Rasmussen
    -0.40
    POSITIVE LOGITS
    featureID
    0.56
     насељу
    0.53
     bedrooms
    0.48
    WebElementEntity
    0.48
     floors
    0.48
     floor
    0.47
     penthouse
    0.47
     propOrder
    0.47
     bedroom
    0.46
     vestibule
    0.46
    Act Density 0.002%

    No Known Activations