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

    Neuronpedia

    INDEX
    Explanations

    titles and nicknames related to places, people, or concepts

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

    Appellations, nicknames, or aliases

    np_acts-logits-general · gemini-2.0-flash

    epithets or alternative names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.51
    دانشنامهٔ
    -0.47
    ArrowToggle
    -0.47
     Autorisations
    -0.45
     abstracta
    -0.39
     queſta
    -0.38
    قایناق‌لار
    -0.37
    vivencia
    -0.37
    Décès
    -0.37
     Autorizaciones
    -0.36
    POSITIVE LOGITS
     nicknamed
    0.80
     dubbed
    0.71
     nickname
    0.60
     nicknames
    0.56
    被称为
    0.52
     “
    0.46
     nazy
    0.45
     disebut
    0.45
     referred
    0.45
    と呼ば
    0.45
    Act Density 0.190%

    No Known Activations