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

    Neuronpedia

    INDEX
    Explanations

    elements related to Facebook and its features or functionality

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

    dates, acronyms, and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lau
    -0.44
     legitimately
    -0.40
     Mats
    -0.40
     Dona
    -0.39
     synergy
    -0.38
     Agu
    -0.38
     F
    -0.38
     Bri
    -0.38
     Fa
    -0.38
    Gua
    -0.38
    POSITIVE LOGITS
     dieß
    0.61
     saveiro
    0.60
    новниш
    0.59
     mijne
    0.59
     EconPapers
    0.57
     campamento
    0.57
     nazwis
    0.56
     itſelf
    0.56
     zijne
    0.56
    fromnode
    0.55
    Act Density 0.018%

    No Known Activations