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

    Neuronpedia

    INDEX
    Explanations

    assertive language and claims about research findings

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

    reporting results and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.62
    Билгалдахарш
    -0.55
    GEBURTSDATUM
    -0.54
    новниш
    -0.52
    KommentareTeilen
    -0.50
    UpInside
    -0.48
     ControllerBase
    -0.48
    Personendaten
    -0.47
    awtextra
    -0.47
    balleur
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.61
     unleashed
    0.40
     bowiem
    0.38
     unleash
    0.37
    SOUNDBITE
    0.37
     werdet
    0.36
    @[+][
    0.36
     saurait
    0.36
     abiertas
    0.35
    বহ
    0.35
    Act Density 0.183%

    No Known Activations