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

    Neuronpedia

    INDEX
    Explanations

    the word "at" in various contexts, particularly regarding location or position

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

    http and url contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.80
     GenerationType
    -0.78
    +#+#
    -0.73
     bezeichneter
    -0.63
    parsedMessage
    -0.62
     /\.(
    -0.61
     uVar
    -0.61
     дописавши
    -0.60
    sizeCache
    -0.59
    bewerken
    -0.59
    POSITIVE LOGITS
     http
    0.34
    estors
    0.34
     at
    0.33
    rsiniz
    0.31
    IntoConstraints
    0.29
     www
    0.29
     https
    0.28
    :
    0.28
    http
    0.28
    Http
    0.27
    Act Density 0.001%

    No Known Activations