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

    Neuronpedia

    INDEX
    Explanations

    pop-up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蒲
    -0.08
     Kay
    -0.08
    ヤ
    -0.07
     muse
    -0.07
     neglect
    -0.07
    relation
    -0.07
     dey
    -0.07
     Greater
    -0.07
    alias
    -0.07
    fet
    -0.07
    POSITIVE LOGITS
     muncul
    0.12
     reminders
    0.12
     окна
    0.12
     verschijnen
    0.11
    提醒
    0.11
     annoy
    0.11
     окно
    0.11
     появляется
    0.11
     alerted
    0.11
     verschijnt
    0.11
    Act Density 0.015%

    No Known Activations