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

    Neuronpedia

    INDEX
    Explanations

    technical references and elements related to software development tools and libraries

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

    user prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.61
     betweenstory
    -0.52
    igshid
    -0.43
     rica
    -0.43
    chromedriver
    -0.43
    eseed
    -0.43
     Diaz
    -0.43
    postsleuth
    -0.41
    jasper
    -0.41
     spoils
    -0.41
    POSITIVE LOGITS
    endalikan
    0.46
     للمعارف
    0.44
    ativement
    0.41
    دانشنامهٔ
    0.41
    обходимо
    0.41
     connaissent
    0.39
     vergüenza
    0.39
     dotyczące
    0.39
     propOrder
    0.39
     moeite
    0.38
    Act Density 0.005%

    No Known Activations