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

    Neuronpedia

    INDEX
    Explanations

    doors and gates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    കളെ
    0.57
     errores
    0.52
    ي
    0.51
     kapital
    0.51
     unterstützen
    0.50
     errori
    0.49
     skup
    0.49
     travaille
    0.47
     arbeiten
    0.47
     junge
    0.46
    POSITIVE LOGITS
    🚪
    1.25
     doors
    1.16
     door
    1.13
    Doors
    1.10
    doors
    1.05
     Door
    1.04
     Doors
    1.04
     двери
    1.04
    ドア
    1.03
    Door
    1.02
    Act Density 0.051%

    No Known Activations