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

    Neuronpedia

    INDEX
    Explanations

    user interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (statement
    -0.08
    (db
    -0.08
     proyectos
    -0.08
     upstream
    -0.08
     establecimientos
    -0.08
    (conn
    -0.08
     обуслов
    -0.07
     eléct
    -0.07
     compromisso
    -0.07
     db
    -0.07
    POSITIVE LOGITS
    HUD
    0.14
     HUD
    0.14
     화면
    0.11
    hud
    0.11
     overlays
    0.10
     स्क्रीन
    0.10
     ekran
    0.10
    屏
    0.10
     hud
    0.09
     anzeigen
    0.09
    Act Density 0.015%

    No Known Activations