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

    Neuronpedia

    INDEX
    Explanations

    beginning of sections or paragraphs

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

    Q. prime. DDT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.52
    plano
    -0.50
    rrggbb
    -0.49
    министра
    -0.47
    SpringBoot
    -0.47
     read
    -0.47
    참고
    -0.46
    akov
    -0.45
    GoogleApiClient
    -0.45
    읽
    -0.44
    POSITIVE LOGITS
    DoubleQuotes
    0.67
     للمعارف
    0.62
    Personendaten
    0.61
     ostavi
    0.59
     EVERYTHING
    0.58
    titur
    0.57
     ISNI
    0.56
     nahilalakip
    0.55
     goe
    0.54
    expandindo
    0.54
    Act Density 0.102%

    No Known Activations